INDEX

Explanations

occurrences where the concept of "separation" is mentioned or implied

oai_token-act-pair · gpt-3.5-turbo

terms associated with separation and differentiation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

odder

-0.93

cycl

-0.63

WR

-0.62

erc

-0.62

PET

-0.62

den

-0.62

DAY

-0.60

LV

-0.60

--+

-0.60

aches

-0.59

POSITIVE LOGITS

 sexes

0.95

iates

0.94

 yourselves

0.85

 oneself

0.85

 distinctions

0.85

iating

0.81

 hairs

0.80

 genders

0.78

iate

0.78

 ourselves

0.75

Activations Density 0.064%

occurrences where the concept of "separation" is mentioned or implied

terms associated with separation and differentiation

No Comments

No Known Activations