INDEX

Explanations

phrases indicating a sense of anticipation or looking forward to future events

oai_token-act-pair · gpt-3.5-turbo

sentences ending or containing punctuation and expressions of conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 inexpl

-0.79

 submerged

-0.76

 abhor

-0.75

 evapor

-0.73

 depl

-0.72

 shun

-0.72

 equivalent

-0.72

 elevated

-0.71

 reflex

-0.71

 tricked

-0.71

POSITIVE LOGITS

 Hopefully

1.32

 Lastly

1.26

 Alternatively

1.14

 Otherwise

1.11

 Ideally

1.10

 Finally

1.08

 Ultimately

1.04

:)

1.00

 Until

0.99

 Personally

0.99

Activations Density 0.423%

phrases indicating a sense of anticipation or looking forward to future events

sentences ending or containing punctuation and expressions of conclusion

No Comments

No Known Activations