INDEX

Explanations

terms related to political resistance

oai_token-act-pair · gpt-3.5-turbo

references to resistance movements and actions against oppression

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

ghazi

-0.83

tein

-0.79

ewater

-0.72

gow

-0.68

 Loaded

-0.68

utra

-0.67

 Lumpur

-0.67

 Pengu

-0.66

orah

-0.66

oba

-0.65

POSITIVE LOGITS

 resistance

0.95

 fighters

0.78

istance

0.75

 Resistance

0.73

 thereto

0.73

 regimes

0.71

yip

0.70

atility

0.70

 dictate

0.70

bands

0.68

Activations Density 0.010%

terms related to political resistance

references to resistance movements and actions against oppression

No Comments

No Known Activations