INDEX

Explanations

references to being native to a place or language

oai_token-act-pair · gpt-3.5-turbo

references to indigenous or native communities and their issues

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

=-=-=-=-

-0.76

ammy

-0.75

awed

-0.75

urat

-0.73

apter

-0.72

enario

-0.72

apego

-0.70

udence

-0.70

ridor

-0.69

ennes

-0.69

POSITIVE LOGITS

 americ

1.00

born

0.83

 Advertisement

0.82

spe

0.79

 Instruments

0.77

izations

0.75

 tongue

0.75

ivated

0.72

izer

0.70

 Hawai

0.69

Activations Density 0.029%

references to being native to a place or language

references to indigenous or native communities and their issues

No Comments

No Known Activations