INDEX

Explanations

paragraph separators, such as "Ċ," in the text

oai_token-act-pair · gpt-3.5-turbo

web navigation elements, specifically links or calls to action

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 instinct

-0.74

 ambassadors

-0.69

 punish

-0.68

mas

-0.68

 regenerate

-0.64

 appar

-0.64

ensibly

-0.63

 rotation

-0.63

 reversing

-0.63

 bending

-0.63

POSITIVE LOGITS

----------------------------------------------------------------

0.91

Tags

0.87

<|endoftext|>

0.86

Conclusion

0.84

SOURCE

0.84

--------------------------------------------------------

0.82

TAG

0.81

-+-+

0.80

================================================================

0.80

Download

0.79

Activations Density 0.543%

paragraph separators, such as "Ċ," in the text

web navigation elements, specifically links or calls to action

No Comments

No Known Activations