INDEX

Explanations

phrases related to important or controversial topics

oai_token-act-pair · gpt-3.5-turbo

references to subjects or topics of discussion or debate

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Towers

-0.80

asters

-0.73

iaries

-0.72

anova

-0.71

orters

-0.69

poons

-0.69

ãĥ³ãĤ¸

-0.67

dp

-0.66

borg

-0.63

endars

-0.63

POSITIVE LOGITS

 itself

0.78

 urgently

0.72

atics

0.71

href

0.71

 posed

0.68

 squarely

0.67

 stemmed

0.65

forth

0.65

fulness

0.64

 vigorously

0.63

Activations Density 0.157%

phrases related to important or controversial topics

references to subjects or topics of discussion or debate

No Comments

No Known Activations