INDEX

Explanations

phrases related to specific individuals or names

oai_token-act-pair · gpt-3.5-turbo

references to the name "Bron."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

URA

-0.78

yrinth

-0.72

uras

-0.69

EPA

-0.65

 Biological

-0.63

stress

-0.60

 Admir

-0.60

 replay

-0.60

EMP

-0.60

ACTION

-0.60

POSITIVE LOGITS

fman

1.18

zes

1.05

wyn

1.03

zos

0.96

neys

0.96

stein

0.91

ze

0.91

hm

0.89

kh

0.89

zon

0.88

Activations Density 0.013%

phrases related to specific individuals or names

references to the name "Bron."

No Comments

No Known Activations