INDEX

Explanations

words related to wars and conflicts

oai_token-act-pair · gpt-3.5-turbo

mentions of various wars, particularly the Second World War

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

obook

-0.77

Row

-0.71

eva

-0.70

OGR

-0.65

tera

-0.65

Tesla

-0.64

ITY

-0.63

aminer

-0.63

*/(

-0.63

afort

-0.62

POSITIVE LOGITS

lords

1.02

lord

0.91

era

0.88

riors

0.85

rior

0.84

bler

0.84

Era

0.81

 Veterans

0.77

fighting

0.77

 Norton

0.76

Activations Density 0.047%

words related to wars and conflicts

mentions of various wars, particularly the Second World War

No Comments

No Known Activations