INDEX

Explanations

names of people or companies

oai_token-act-pair · gpt-3.5-turbo

proper names of individuals, specifically related to media or news contexts

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

 hikers

-0.62

 Reincarn

-0.60

Bird

-0.60

(?,

-0.59

lication

-0.58

âĵĺ

-0.56

dfx

-0.56

represented

-0.54

Footnote

-0.53

Scotland

-0.53

POSITIVE LOGITS

(@

0.86

enegger

0.85

zinski

0.79

atz

0.75

 Photography

0.73

icut

0.69

 contributed

0.67

EStreamFrame

0.66

overe

0.66

ourke

0.64

Activations Density 0.202%

names of people or companies

proper names of individuals, specifically related to media or news contexts

No Comments

No Known Activations