INDEX

Explanations

negative values or words related to military actions

oai_token-act-pair · gpt-3.5-turbo

the end of a document or a clear division between sections

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

 Norris

-0.60

kson

-0.53

 ausp

-0.53

 Emerson

-0.50

 Debor

-0.49

ãĥ¼ãĥĨ

-0.49

 proport

-0.49

 Arabian

-0.49

 Dickinson

-0.48

Peb

-0.48

POSITIVE LOGITS

tailed

0.84

mounted

0.83

sized

0.81

hander

0.75

initialized

0.75

unit

0.74

themed

0.73

machine

0.73

level

0.72

eyed

0.72

Activations Density 0.163%

negative values or words related to military actions

the end of a document or a clear division between sections

No Comments

No Known Activations