INDEX

Explanations

mentions of articles or written pieces

oai_token-act-pair · gpt-3.5-turbo

references to articles, posts, and various forms of media or content

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

Not in Any Lists

No Comments

Negative Logits

externalActionCode

-0.76

innie

-0.58

ntil

-0.58

cale

-0.57

ãģĨ

-0.57

lap

-0.56

ECA

-0.56

actionDate

-0.56

rero

-0.55

Lago

-0.55

POSITIVE LOGITS

 concludes

1.25

 progresses

1.24

 itself

1.24

 focuses

1.17

 begins

1.17

 culmin

1.16

 depicts

1.14

 revolves

1.13

 ends

1.12

 contains

1.10

Activations Density 0.238%

mentions of articles or written pieces

references to articles, posts, and various forms of media or content

No Comments

No Known Activations