INDEX

Explanations

mentions of the word "Second" followed by a comma, indicating a new point or item in a list

oai_token-act-pair · gpt-3.5-turbo

instances of the word "second."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Bind

-0.73

AGE

-0.73

ãĥĥãĥī

-0.68

owe

-0.67

CPU

-0.66

Deal

-0.65

owed

-0.64

Continue

-0.64

st

-0.62

scribe

-0.62

POSITIVE LOGITS

 unlike

0.94

 insofar

0.91

 although

0.91

 there

0.82

 interestingly

0.79

 besides

0.78

 namely

0.77

 despite

0.76

 lest

0.76

 suppose

0.74

Activations Density 0.128%

mentions of the word "Second" followed by a comma, indicating a new point or item in a list

instances of the word "second."

No Comments

No Known Activations