INDEX

Explanations

words related to technology and projects, potentially involving proper nouns

oai_token-act-pair · gpt-3.5-turbo

specific titles and names related to media and entertainment

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

 sqor

-0.68

 Benz

-0.62

 WARN

-0.57

otos

-0.56

emi

-0.55

tl

-0.55

atically

-0.55

ported

-0.54

 Nielsen

-0.54

yg

-0.54

POSITIVE LOGITS

istries

0.81

Ħ¢

0.80

astery

0.76

ħĭ

0.71

APTER

0.66

 Series

0.66

 Association

0.65

 Prix

0.65

 Tycoon

0.65

atum

0.63

Activations Density 0.301%

words related to technology and projects, potentially involving proper nouns

specific titles and names related to media and entertainment

No Comments

No Known Activations