INDEX

Explanations

locations, institutions, or objects that are the same or identical

oai_token-act-pair · gpt-3.5-turbo

references to shared experiences or commonalities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cknowled

-0.64

 Uriel

-0.60

cknow

-0.56

Gau

-0.56

 candid

-0.54

hen

-0.53

tiny

-0.53

 palp

-0.53

TAG

-0.52

 Wiki

-0.52

POSITIVE LOGITS

nings

0.76

iatus

0.72

kefeller

0.71

same

0.68

ozo

0.67

rant

0.65

ulative

0.65

vier

0.65

amazon

0.65

 Tradable

0.63

Activations Density 0.148%

locations, institutions, or objects that are the same or identical

references to shared experiences or commonalities

No Comments

No Known Activations