INDEX

Explanations

the word "new" appearing in the text

oai_token-act-pair · gpt-3.5-turbo

references to the concept of something being "new."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

verning

-0.71

weeney

-0.66

ignt

-0.66

 awoken

-0.63

YES

-0.62

+++

-0.60

nos

-0.60

 attm

-0.59

afia

-0.59

rior

-0.58

POSITIVE LOGITS

nor

0.99

 either

0.72

 phenomenon

0.70

 charism

0.70

rences

0.64

MpServer

0.63

 occurrence

0.63

 controversy

0.63

.}

0.62

 anymore

0.62

Activations Density 0.114%

the word "new" appearing in the text

references to the concept of something being "new."

No Comments

No Known Activations