INDEX

Explanations

references to Russian President Vladimir Putin

oai_token-act-pair · gpt-3.5-turbo

mentions of Vladimir Putin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Fargo

-0.77

ANE

-0.76

Thom

-0.69

 Tolkien

-0.69

CRE

-0.68

------------------------------------------------

-0.67

mel

-0.66

Native

-0.64

AAA

-0.64

 Freddie

-0.64

POSITIVE LOGITS

 Jinping

1.42

 himself

1.10

 confid

1.00

omics

0.89

 Himself

0.87

 personally

0.86

 aide

0.85

ovich

0.85

 loyal

0.83

 supporters

0.83

Activations Density 0.121%

references to Russian President Vladimir Putin

mentions of Vladimir Putin

No Comments

No Known Activations