INDEX

Explanations

negative words associated with deception and misinformation

oai_token-act-pair · gpt-3.5-turbo

references to misinformation and its effects

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GOODMAN

-0.86

ufact

-0.79

natureconservancy

-0.78

hesion

-0.74

Temperature

-0.72

ederation

-0.72

entary

-0.71

bridge

-0.70

gio

-0.69

pection

-0.68

POSITIVE LOGITS

 perpetrated

1.03

 slander

0.96

 insin

0.92

 baseless

0.91

 disinformation

0.91

 accusations

0.91

 misinformation

0.90

 falsehood

0.88

 bigotry

0.88

 bigot

0.88

Activations Density 0.778%

negative words associated with deception and misinformation

references to misinformation and its effects

No Comments

No Known Activations