INDEX

Explanations

mentions of the word "Disney"

oai_token-act-pair · gpt-3.5-turbo

key terms and names associated with Disney-related content

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

 Papers

-0.76

 Bened

-0.75

ulo

-0.74

INAL

-0.71

gil

-0.69

 Journalism

-0.66

entry

-0.65

 unfocusedRange

-0.62

 Cities

-0.62

 Goals

-0.60

POSITIVE LOGITS

inki

0.74

velt

0.66

DonaldTrump

0.59

 Betsy

0.58

 laun

0.57

 Lanka

0.56

esses

0.56

Sund

0.56

OULD

0.55

iker

0.55

Activations Density 0.535%

mentions of the word "Disney"

key terms and names associated with Disney-related content

No Comments

No Known Activations