INDEX

Explanations

texts related to the abbreviation "AC"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

doms

-0.83

bush

-0.80

hood

-0.74

glers

-0.74

ozyg

-0.72

jar

-0.71

 Tradable

-0.69

hs

-0.69

lihood

-0.66

 Fenrir

-0.64

POSITIVE LOGITS

ORN

1.12

CEPT

1.02

APTER

0.98

oustic

0.90

HE

0.87

ME

0.87

UTE

0.85

GRE

0.84

ATA

0.84

OSS

0.83

Activations Density 0.024%

texts related to the abbreviation "AC"

No Comments

No Known Activations