INDEX

Explanations

mentions of something being special in some context

oai_token-act-pair · gpt-3.5-turbo

the concept of "special."

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

•Special

No Comments

Negative Logits

 Twain

-0.69

Ri

-0.66

anon

-0.65

 Giul

-0.65

Cah

-0.63

Ķ

-0.63

Cao

-0.62

amus

-0.61

Į

-0.60

·

-0.60

POSITIVE LOGITS

ised

1.15

ties

1.00

izations

0.96

isations

0.95

isable

0.90

ized

0.89

marine

0.84

ities

0.83

isal

0.81

atural

0.81

Activations Density 0.022%

mentions of something being special in some context

the concept of "special."

No Comments

No Known Activations