INDEX

Explanations

phrases related to laws, regulations, and oppositions

oai_token-act-pair · gpt-3.5-turbo

terms related to legal processes or implications

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

 Warp

-0.69

 Helm

-0.68

 Jagu

-0.65

BuyableInstoreAndOnline

-0.65

 Abbas

-0.63

 Chop

-0.63

 Spark

-0.62

åī

-0.61

åĳ

-0.60

 Codec

-0.58

POSITIVE LOGITS

ruary

1.22

ividual

1.17

erent

1.14

ecause

1.08

icient

1.06

nesday

1.06

ould

1.04

 tion

1.04

pecially

1.03

sic

1.03

Activations Density 0.751%

phrases related to laws, regulations, and oppositions

terms related to legal processes or implications

No Comments

No Known Activations