INDEX

Explanations

mentions of companies and brand names

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or organizations in the context of activism or discrimination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

earchers

-0.80

©¶æ

-0.80

blance

-0.75

 dime

-0.72

ĸļ

-0.71

ources

-0.68

enthal

-0.67

atives

-0.66

ommel

-0.66

hend

-0.64

POSITIVE LOGITS

iar

0.72

ãģĤ

0.63

Cola

0.63

à¤¾

0.62

iasco

0.61

 knees

0.60

 Playoff

0.59

à¤

0.58

 bananas

0.57

ãĤ¬

0.57

Activations Density 0.364%

mentions of companies and brand names

references to specific individuals or organizations in the context of activism or discrimination

No Comments

No Known Activations