INDEX

Explanations

references to geopolitical relations between Russia and other countries or entities

oai_token-act-pair · gpt-3.5-turbo

references to Russian influence and involvement in various contexts

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

 "$:/

-0.77

 stub

-0.73

rake

-0.65

 Dickinson

-0.65

 Died

-0.64

 jars

-0.62

isode

-0.62

 antidote

-0.60

arers

-0.60

 youngest

-0.59

POSITIVE LOGITS

Äĩ

0.95

kaya

0.94

Äį

0.86

Ð¼

0.85

 Serbia

0.82

 Monteneg

0.81

 Lavrov

0.80

achev

0.80

Sat

0.78

odan

0.78

Activations Density 0.342%

references to geopolitical relations between Russia and other countries or entities

references to Russian influence and involvement in various contexts

No Comments

No Known Activations