INDEX

Explanations

proper nouns or names, potentially related to show business

oai_token-act-pair · gpt-3.5-turbo

prominent names of individuals in the entertainment industry

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

alist

-0.82

ery

-0.81

ansas

-0.79

ibel

-0.79

uador

-0.76

ĸļ

-0.75

igans

-0.74

pie

-0.72

ist

-0.72

mare

-0.72

POSITIVE LOGITS

zzi

0.82

 Adin

0.73

 Remastered

0.71

CHR

0.66

 Tycoon

0.64

 Bagg

0.63

 Vacc

0.61

 Romero

0.60

 Bened

0.59

 circumcised

0.59

Activations Density 0.058%

proper nouns or names, potentially related to show business

prominent names of individuals in the entertainment industry

No Comments

No Known Activations