INDEX

Explanations

phrases related to specific body parts

oai_token-act-pair · gpt-3.5-turbo

references to shared experiences and collective identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

words

-0.66

erest

-0.64

Enabled

-0.62

word

-0.61

ocre

-0.61

frog

-0.60

Same

-0.59

nil

-0.58

cair

-0.57

!!!!!!!!

-0.57

POSITIVE LOGITS

 accompanying

0.94

 consequ

0.71

 ensuing

0.71

 attendant

0.70

 associated

0.68

 surrounding

0.68

 subsequent

0.66

 rest

0.64

 resultant

0.64

 judiciary

0.62

Activations Density 0.909%

phrases related to specific body parts

references to shared experiences and collective identities

No Comments

No Known Activations