INDEX

Explanations

proper nouns related to specific locations, such as "Beverly" and "Pasadena."

oai_token-act-pair · gpt-3.5-turbo

mentions of specific locations or cities, particularly those in California

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

zik

-0.86

 Wolves

-0.80

 Titan

-0.76

 Moose

-0.72

PKK

-0.72

 Golem

-0.71

 memes

-0.71

react

-0.70

 minion

-0.70

mining

-0.69

POSITIVE LOGITS

 Beverly

3.74

 Pasadena

1.76

 Venice

1.41

ibu

1.29

 Jackie

1.21

 LAPD

1.21

 Sandra

1.19

 Gloria

1.17

 Bever

1.15

 affirmative

1.14

Activations Density 0.043%

proper nouns related to specific locations, such as "Beverly" and "Pasadena."

mentions of specific locations or cities, particularly those in California

No Comments

No Known Activations