INDEX

Explanations

references to opinions or statements made by different individuals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating possession or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Champ

-0.69

MX

-0.65

<?

-0.62

ocene

-0.60

Written

-0.58

CHAT

-0.56

////////////////////////////////

-0.56

sew

-0.56

kat

-0.55

ãĤ¼ãĤ¦ãĤ¹

-0.54

POSITIVE LOGITS

 course

0.85

 sorts

0.81

course

0.71

¥µ

0.71

elia

0.65

una

0.65

ilities

0.62

 those

0.61

edly

0.61

the

0.61

Activations Density 0.057%

references to opinions or statements made by different individuals

phrases indicating possession or association

No Comments

No Known Activations