INDEX

Explanations

mentions of wars and military references

oai_token-act-pair · gpt-3.5-turbo

references to various types of wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ĸļ

-0.93

sembly

-0.76

essee

-0.71

Ħ¢

-0.70

İĭ

-0.69

 tremend

-0.69

URES

-0.68

aminer

-0.66

 kindred

-0.66

 extrad

-0.64

POSITIVE LOGITS

riors

1.40

rior

1.31

fare

1.31

war

1.24

ring

1.13

lords

0.92

fighter

0.92

lord

0.90

bucks

0.90

far

0.87

Activations Density 0.006%

mentions of wars and military references

references to various types of wars

No Comments

No Known Activations