INDEX

Explanations

Japanese names and some other specific personal and geographical names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and organizations

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

ishes

-0.60

 undo

-0.59

tein

-0.59

 Frog

-0.57

 Turing

-0.56

 spawning

-0.56

DPS

-0.56

odder

-0.55

MIA

-0.55

 fingerprints

-0.55

POSITIVE LOGITS

acan

0.84

æ©

0.79

etus

0.76

VT

0.76

é¾įå

0.75

umerable

0.75

Lenin

0.71

hoe

0.70

ACA

0.70

idis

0.69

Activations Density 0.118%

Japanese names and some other specific personal and geographical names

proper nouns, specifically names and organizations

No Comments

No Known Activations