INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 USPS

-0.74

-0.68

 Lucy

-0.66

 Dire

-0.62

 Adjusted

-0.61

Reloaded

-0.60

 PlayStation

-0.60

CLS

-0.59

 Glob

-0.59

 Competition

-0.58

POSITIVE LOGITS

aney

0.88

amiya

0.87

acci

0.84

onson

0.83

eson

0.81

indal

0.81

mberg

0.80

ivan

0.79

rake

0.79

kowski

0.79

Activations Density 0.077%

names of individuals

proper nouns, specifically names of individuals

No Comments

No Known Activations