INDEX

Explanations

references to the city of Los Angeles (LA)

oai_token-act-pair · gpt-3.5-turbo

references to Los Angeles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lers

-0.90

vous

-0.74

ler

-0.70

thood

-0.69

lication

-0.68

xual

-0.66

books

-0.66

cription

-0.65

manship

-0.63

 Britann

-0.63

POSITIVE LOGITS

UNCH

1.43

UGH

1.16

USD

1.08

URA

1.06

 Galaxy

1.06

KE

1.04

0.97

 Clippers

0.91

FC

0.90

 Angeles

0.84

Activations Density 0.027%

references to the city of Los Angeles (LA)

references to Los Angeles

No Comments

No Known Activations