INDEX

Explanations

phrases related to general concepts or issues

oai_token-act-pair · gpt-3.5-turbo

the word "in" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ername

-0.66

FTWARE

-0.62

ensical

-0.60

 entit

-0.57

 accordingly

-0.57

jri

-0.57

dule

-0.57

-0.56

 sidx

-0.56

#$

-0.56

POSITIVE LOGITS

 general

1.38

 particular

1.24

 nutshell

1.18

efficiency

1.07

clus

1.01

clusions

0.98

effic

0.98

version

0.87

versions

0.84

 America

0.83

Activations Density 0.222%

phrases related to general concepts or issues

the word "in" across various contexts

No Comments

No Known Activations