INDEX

Explanations

words related to conflicting or contradictory information

oai_token-act-pair · gpt-3.5-turbo

references to conflicting information or reports

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

chens

-0.81

abit

-0.79

rix

-0.76

aday

-0.76

fm

-0.75

ney

-0.74

frey

-0.74

bern

-0.73

rection

-0.73

adr

-0.73

POSITIVE LOGITS

 conflicting

1.57

 contradictory

1.30

 undermin

0.99

 discrep

0.97

 conflicted

0.93

 conflicts

0.89

 sexes

0.88

 guiActiveUn

0.85

 predic

0.84

 opinions

0.83

Activations Density 0.010%

words related to conflicting or contradictory information

references to conflicting information or reports

No Known Activations