INDEX

Explanations

mentions of historical events or wars, specifically World War II

oai_token-act-pair · gpt-3.5-turbo

mentions of historical wars, particularly World Wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

obook

-0.77

aminer

-0.70

uckland

-0.68

OGR

-0.67

Choice

-0.64

*/(

-0.62

ITY

-0.60

Asset

-0.60

66666666

-0.59

à

-0.58

POSITIVE LOGITS

riors

0.94

lords

0.93

lord

0.92

rior

0.85

fare

0.79

II

0.76

 Patton

0.74

bler

0.74

rell

0.71

III

0.71

Activations Density 0.014%

mentions of historical events or wars, specifically World War II

mentions of historical wars, particularly World Wars

No Comments

No Known Activations