INDEX

Explanations

proper nouns mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Walsh" in the text

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

arial

-0.89

 explanatory

-0.79

egal

-0.78

uate

-0.78

arily

-0.74

 fortun

-0.72

 illum

-0.71

 coerc

-0.69

ĪĴ

-0.69

alien

-0.68

POSITIVE LOGITS

 Walsh

0.96

enegger

0.93

restling

0.81

bands

0.81

 Baldwin

0.78

mann

0.76

ashington

0.76

enance

0.74

gaard

0.74

 Norton

0.74

Activations Density 0.021%

proper nouns mentioned in the text

occurrences of the name "Walsh" in the text

No Comments

No Known Activations