INDEX

Explanations

words related to warfare

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "war"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

-0.95

sembly

-0.90

Ħ¢

-0.84

aminer

-0.82

ħĭ

-0.82

İĭ

-0.81

etsk

-0.75

aunder

-0.72

hiba

-0.70

issance

-0.69

POSITIVE LOGITS

rior

1.29

fare

1.27

lords

1.22

riors

1.21

lord

1.17

locks

1.03

ped

0.94

ring

0.94

ping

0.92

bands

0.88

Activations Density 0.029%

words related to warfare

references to the concept of "war"

No Comments

No Known Activations