INDEX

Explanations

terms related to academic fields of study and research

oai_token-act-pair · gpt-3.5-turbo

terms related to various academic disciplines and social issues

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

guyen

-0.70

 saline

-0.60

OUNT

-0.57

REAM

-0.55

ificant

-0.54

 pestic

-0.54

irlf

-0.54

 confir

-0.53

 unnamed

-0.53

idav

-0.53

POSITIVE LOGITS

anship

0.92

 etiquette

0.73

manship

0.72

smanship

0.70

utics

0.68

itaire

0.68

istry

0.66

entry

0.66

,...

0.64

boarding

0.64

Activations Density 0.506%

terms related to academic fields of study and research

terms related to various academic disciplines and social issues

No Comments

No Known Activations