INDEX

Explanations

names of political figures

oai_token-act-pair · gpt-3.5-turbo

the names of political figures and candidates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

eric

-0.81

gery

-0.70

ptin

-0.67

 Sven

-0.66

 Collective

-0.66

vered

-0.66

itual

-0.65

 ISBN

-0.65

 Clubs

-0.64

racted

-0.64

POSITIVE LOGITS

asse

0.72

taboola

0.68

 reacts

0.65

Senate

0.65

CLOSE

0.62

 listens

0.59

Null

0.59

ENN

0.59

avanaugh

0.58

Poll

0.58

Activations Density 0.066%

names of political figures

the names of political figures and candidates

No Comments

No Known Activations