INDEX

Explanations

geographical locations, specifically in Wisconsin

oai_token-act-pair · gpt-3.5-turbo

references to the state of Wisconsin

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ion

-0.80

inant

-0.77

izoph

-0.74

icably

-0.74

ainer

-0.73

ourge

-0.72

izers

-0.71

inators

-0.70

angelo

-0.68

inates

-0.68

POSITIVE LOGITS

manship

0.95

pered

0.91

Wis

0.88

eman

0.86

pering

0.85

WI

0.74

gets

0.73

Fed

0.71

isconsin

0.68

Pis

0.68

Activations Density 0.056%

geographical locations, specifically in Wisconsin

references to the state of Wisconsin

No Comments

No Known Activations