INDEX

Explanations

sequential numbers or dates

oai_token-act-pair · gpt-3.5-turbo

numeric values and statistics related to various topics

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

 skelet

-0.64

 UNCLASSIFIED

-0.61

 exting

-0.58

 disadvant

-0.57

âķĲ

-0.57

CONCLUS

-0.55

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.53

Conclusion

-0.53

pse

-0.53

 welf

-0.52

POSITIVE LOGITS

 [âĢ¦]

0.66

 âĢİ

0.62

âĢİ

0.59

 Posted

0.56

0.53

 âĢº

0.53

 Donald

0.49

 frontman

0.48

 Thursday

0.48

 cryptocurrency

0.47

Activations Density 5.818%

sequential numbers or dates

numeric values and statistics related to various topics

No Comments

No Known Activations