INDEX

Explanations

phrases indicating approval or authorization

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "sign off."

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

Gall

-0.64

ãĥĸ

-0.63

Export

-0.62

 Eisenhower

-0.59

ãĥį

-0.58

 Mate

-0.58

geries

-0.58

ãĥ¼ãĥĨãĤ£

-0.57

CU

-0.56

ilation

-0.56

POSITIVE LOGITS

shoot

0.89

MENTS

0.79

spr

0.79

ments

0.79

MENT

0.78

beat

0.78

ment

0.76

cffffcc

0.75

undown

0.72

sites

0.71

Activations Density 0.041%

phrases indicating approval or authorization

instances of the phrase "sign off."

No Comments

No Known Activations