INDEX

Explanations

words related to propaganda and misinformation

oai_token-act-pair · gpt-3.5-turbo

references to propaganda and its various forms and contexts

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

ergy

-0.80

heed

-0.73

cker

-0.70

berry

-0.68

 Eucl

-0.68

hens

-0.68

clud

-0.68

kens

-0.68

 Roses

-0.67

gger

-0.66

POSITIVE LOGITS

aganda

1.11

 posters

0.86

 leaflets

0.85

 propaganda

0.84

 dissemin

0.83

 suppression

0.81

 dissemination

0.80

 disinformation

0.79

 blitz

0.79

isSpecialOrderable

0.75

Activations Density 0.025%

words related to propaganda and misinformation

references to propaganda and its various forms and contexts

No Comments

No Known Activations