INDEX

Explanations

mentions of a television or radio program

oai_token-act-pair · gpt-3.5-turbo

references to television shows

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

etheless

-0.95

 litter

-0.79

assing

-0.72

 saline

-0.71

 bilingual

-0.70

 tactile

-0.69

 mint

-0.69

axy

-0.69

 notor

-0.69

 redundancy

-0.68

POSITIVE LOGITS

biz

1.23

case

1.19

alter

1.13

cases

1.10

 Tycoon

1.07

runners

1.01

ing

0.97

grounds

0.92

boat

0.90

runner

0.86

Activations Density 0.022%

mentions of a television or radio program

references to television shows

No Comments

No Known Activations