INDEX

Explanations

words related to spatial positioning or location, particularly when something is next to or beside something else

oai_token-act-pair · gpt-3.5-turbo

the word "beside" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

izens

-0.71

egal

-0.68

ized

-0.66

uese

-0.65

izers

-0.65

NING

-0.64

 Reloaded

-0.63

anwhile

-0.63

 transmissions

-0.63

ordan

-0.63

POSITIVE LOGITS

 hers

0.84

phant

0.81

ĸļ

0.80

lihood

0.78

perty

0.74

DonaldTrump

0.73

 theirs

0.73

 Hats

0.69

whel

0.68

İĭ

0.68

Activations Density 0.010%

words related to spatial positioning or location, particularly when something is next to or beside something else

the word "beside" and its variations

No Comments

No Known Activations