INDEX

Explanations

proper nouns related to specific locations or characters

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and locations

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

Rex

-0.74

 mush

-0.69

 Zack

-0.64

Nig

-0.64

 Joshua

-0.64

manac

-0.63

 Judah

-0.63

 Tank

-0.63

fu

-0.63

 Cart

-0.62

POSITIVE LOGITS

holm

4.01

helm

1.24

obyl

1.20

meier

1.16

vard

1.08

ovan

1.07

 Janeiro

1.04

agos

1.03

ÙĪ

0.97

 Dreams

0.96

Activations Density 0.063%

proper nouns related to specific locations or characters

proper nouns, particularly names and locations

No Comments

No Known Activations