INDEX

Explanations

instances of the word "or."

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

the word "or"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ires

-0.70

Ident

-0.65

IDENT

-0.64

ETS

-0.62

efer

-0.62

IGHTS

-0.60

 Pony

-0.60

mitter

-0.59

moil

-0.59

EMP

-0.58

POSITIVE LOGITS

nam

1.22

acle

1.19

chard

1.17

chid

1.12

ifice

1.09

acles

1.08

Else

1.02

nery

0.99

ific

0.99

 otherwise

0.97

Activations Density 0.180%

instances of the word "or."

the word "or"

No Comments

No Known Activations