INDEX

Explanations

phrases related to propaganda

oai_token-act-pair · gpt-3.5-turbo

mentions of propaganda and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

kens

-0.79

bang

-0.70

heed

-0.69

thur

-0.68

ESV

-0.67

IFE

-0.67

aird

-0.66

clud

-0.66

ighth

-0.66

aldo

-0.66

POSITIVE LOGITS

 campaigns

1.14

 propaganda

1.01

 leaflets

0.98

 disinformation

0.97

aganda

0.96

 dissemin

0.96

 posters

0.94

eering

0.93

 tactics

0.93

 ploy

0.92

Activations Density 0.068%

phrases related to propaganda

mentions of propaganda and related concepts

No Comments

No Known Activations