INDEX

Explanations

mentions of venues or locations associated with events

oai_token-act-pair · gpt-3.5-turbo

references to specific brands or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 induct

-0.69

 methodological

-0.69

 defin

-0.68

 Dickinson

-0.68

anners

-0.64

anguage

-0.63

 procedural

-0.63

 dissenting

-0.62

 chamber

-0.61

 rooting

-0.61

POSITIVE LOGITS

Cola

1.06

Benz

1.04

France

1.01

esque

0.95

Sol

0.95

Lago

0.94

Pal

0.90

induced

0.90

sama

0.89

sized

0.87

Activations Density 0.092%

mentions of venues or locations associated with events

references to specific brands or products

No Comments

No Known Activations