INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

words related to identities or notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

utations

-0.73

 Padres

-0.72

 Ventura

-0.69

 PROT

-0.69

ãĤº

-0.66

 Vide

-0.66

 BASE

-0.65

-0.64

 Static

-0.63

-0.62

POSITIVE LOGITS

haw

1.21

1.18

hur

1.11

hatt

1.09

har

1.07

hap

1.04

hw

1.04

hat

1.01

him

0.98

hew

0.98

Activations Density 0.242%

names of individuals

words related to identities or notable individuals

No Comments

No Known Activations