INDEX

Explanations

terms related to military and political organizations

oai_token-act-pair · gpt-3.5-turbo

words related to military or armed conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

swer

-0.69

egg

-0.66

 patiently

-0.65

nces

-0.65

cond

-0.64

smanship

-0.64

words

-0.64

 withstand

-0.63

 Vive

-0.63

BOOK

-0.63

POSITIVE LOGITS

ament

1.05

assed

0.97

eral

0.95

uary

0.91

rative

0.90

acion

0.89

arist

0.88

atem

0.88

ooter

0.87

agement

0.87

Activations Density 0.013%

terms related to military and political organizations

words related to military or armed conflict

No Comments

No Known Activations