INDEX

Explanations

the string "Gro" at the start of a word

oai_token-act-pair · gpt-4-turbo

mentions of the word "Gro"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Gro" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

manship

-0.70

 Hurricanes

-0.69

CPC

-0.67

 PowerPoint

-0.66

 Leilan

-0.64

uyomi

-0.63

 christ

-0.63

FAA

-0.63

 EDITION

-0.62

ACA

-0.60

POSITIVE LOGITS

ovy

1.18

tesque

1.09

cery

1.06

ove

1.02

hett

0.93

ggy

0.91

azy

0.91

Gro

0.91

lean

0.88

bie

0.86

Activations Density 0.004%

the string "Gro" at the start of a word

mentions of the word "Gro"

references to the name "Gro" in various contexts

No Comments

No Known Activations