INDEX

Explanations

technical terms or jargon related to specific organizations or entities

oai_token-act-pair · gpt-3.5-turbo

the abbreviation "NA" frequently used in various contexts

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

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

birds

-0.88

papers

-0.78

thumbnails

-0.78

ãĤ©

-0.76

ienced

-0.75

library

-0.75

starter

-0.74

geist

-0.72

======

-0.70

circle

-0.69

POSITIVE LOGITS

ZI

1.28

NA

1.07

ACP

1.07

FU

1.00

VIDIA

0.90

BLE

0.89

VE

0.84

ISS

0.80

BER

0.79

GA

0.79

Activations Density 0.005%

technical terms or jargon related to specific organizations or entities

the abbreviation "NA" frequently used in various contexts

No Comments

No Known Activations