INDEX

Explanations

capitalized words indicating titles or headings

oai_token-act-pair · gpt-3.5-turbo

references to specific games or game-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 understatement

-0.65

hement

-0.65

 guts

-0.64

 lashes

-0.61

Khe

-0.60

lou

-0.60

 toget

-0.59

 famously

-0.59

 grocer

-0.58

 thought

-0.58

POSITIVE LOGITS

âĨĳ

1.19

References

1.13

External

0.99

Footnote

0.95

Further

0.92

Credits

0.92

Fall

0.90

Sources

0.90

Resources

0.88

Production

0.87

Activations Density 0.099%

capitalized words indicating titles or headings

references to specific games or game-related content

No Comments

No Known Activations