INDEX

Explanations

names of people's initials

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and initials associated with people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 constitu

-0.68

oslav

-0.65

 veins

-0.64

glers

-0.61

é¾įåĸļå£«

-0.60

 Flavoring

-0.60

 resid

-0.59

 runes

-0.59

UFF

-0.59

 enthus

-0.57

POSITIVE LOGITS

rama

0.79

enment

0.76

amins

0.75

ĳå£«

0.73

ente

0.72

asaki

0.72

heid

0.71

zeb

0.71

gui

0.70

amina

0.69

Activations Density 0.062%

names of people's initials

proper nouns, specifically names and initials associated with people or entities

No Comments

No Known Activations