INDEX

Explanations

phrases related to topics, subjects, debates, or discussions in a document

oai_token-act-pair · gpt-3.5-turbo

phrases related to topics of discussion or subjects of curiosity

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ents

-0.74

uez

-0.66

ãĥīãĥ©

-0.65

PG

-0.63

 Components

-0.61

hing

-0.61

ITH

-0.61

oline

-0.61

frog

-0.61

loo

-0.60

POSITIVE LOGITS

 fascination

1.26

 ridicule

1.26

 contention

1.20

ire

1.16

 discussion

1.15

 scorn

1.14

 mockery

1.13

 conversation

1.12

 debate

1.09

 scrutiny

1.09

Activations Density 0.121%

phrases related to topics, subjects, debates, or discussions in a document

phrases related to topics of discussion or subjects of curiosity

No Known Activations