INDEX

Explanations

words related to armed conflict or war

oai_token-act-pair · gpt-3.5-turbo

mentions of war and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

essee

-0.78

 Universe

-0.69

gow

-0.68

AME

-0.66

 Thumbnails

-0.65

 drawer

-0.64

ħĭ

-0.62

 Collider

-0.61

aminer

-0.61

*/(

-0.61

POSITIVE LOGITS

lords

1.33

lord

1.27

fare

1.20

rior

1.15

riors

1.12

ring

1.06

zone

1.05

fighting

1.05

 waged

1.00

ping

1.00

Activations Density 0.052%

words related to armed conflict or war

mentions of war and related concepts

No Comments

No Known Activations