INDEX

Explanations

phrases related to introductions or headings followed by a strong call to action

oai_token-act-pair · gpt-3.5-turbo

sections indicating a list or breakdown of information

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

natureconservancy

-0.71

ãĥı

-0.63

DEP

-0.58

rals

-0.56

EAR

-0.55

Ct

-0.55

æ©

-0.54

 Confeder

-0.54

é¾įå¥ĳå£«

-0.54

cill

-0.53

POSITIVE LOGITS

are

1.10

 Thumbnails

0.94

is

0.94

you

0.80

neath

0.77

 depicts

0.74

 denotes

0.71

 summarizes

0.70

ground

0.70

 tables

0.69

Activations Density 0.038%

phrases related to introductions or headings followed by a strong call to action

sections indicating a list or breakdown of information

No Comments

No Known Activations