INDEX

Explanations

words related to individuals or entities, specifically focusing on proper nouns related to names and titles

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

people's names or location names ending with 'row'

oai_token-act-pair · gpt-3.5-turbo

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

Negative Logits

ngth

-0.73

dimension

-0.68

ascus

-0.65

bern

-0.64

shape

-0.63

URA

-0.63

 Remastered

-0.62

iland

-0.62

Drive

-0.59

ĨĴ

-0.57

POSITIVE LOGITS

enture

0.76

aroo

0.74

 Explosion

0.67

hea

0.65

ĵĺ

0.65

 teasp

0.64

 Admission

0.64

oola

0.64

hemy

0.63

ħĭ

0.63

Activations Density 0.101%

words related to individuals or entities, specifically focusing on proper nouns related to names and titles

people's names or location names ending with 'row'

No Known Activations