INDEX

Explanations

references to Russian President Vladimir Putin

oai_token-act-pair · gpt-3.5-turbo

references to Vladimir Putin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

dress

-0.83

aver

-0.72

BACK

-0.72

eat

-0.71

alach

-0.70

cular

-0.69

pel

-0.68

dash

-0.67

kick

-0.67

cule

-0.65

POSITIVE LOGITS

 Putin

1.27

 Vladimir

1.15

 Vlad

1.05

 Jinping

1.04

 Dmitry

1.03

Ily

1.02

Nab

0.97

 Lenin

0.90

 Tayyip

0.87

 Dmit

0.85

Activations Density 0.004%

references to Russian President Vladimir Putin

references to Vladimir Putin

No Comments

No Known Activations