INDEX

Explanations

references to professionals or professionalism

oai_token-act-pair · gpt-3.5-turbo

mentions of professionalism and related professional contexts

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

edin

-0.88

ĸļ

-0.78

apo

-0.75

tags

-0.73

ource

-0.67

doors

-0.66

adr

-0.65

 Wick

-0.65

 Twain

-0.64

LIB

-0.64

POSITIVE LOGITS

 wrestler

1.07

 athlete

1.02

digy

1.00

 athletes

0.97

 footballer

0.96

 wrestling

0.94

 Wrest

0.90

gol

0.89

ized

0.87

 Wrestling

0.85

Activations Density 0.025%

references to professionals or professionalism

mentions of professionalism and related professional contexts

No Comments

No Known Activations