INDEX

Explanations

words related to acting and actors

oai_token-act-pair · gpt-3.5-turbo

instances of the word "act" in various contexts

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

 habitable

-0.70

 custody

-0.70

Ń·

-0.69

ciating

-0.69

 leveled

-0.69

 dove

-0.64

phia

-0.64

 Haram

-0.63

 referen

-0.63

£ı

-0.63

POSITIVE LOGITS

ional

1.27

uary

1.22

ual

0.98

uated

0.96

uation

0.96

uin

0.95

ors

0.92

uate

0.89

iop

0.89

uating

0.89

Activations Density 0.021%

words related to acting and actors

instances of the word "act" in various contexts

No Comments

No Known Activations