INDEX

Explanations

No Explanations Found

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

zed

-0.81

igate

-0.80

ATIONAL

-0.69

 largeDownload

-0.69

brates

-0.66

abases

-0.66

ipel

-0.66

 AMER

-0.66

ATED

-0.65

igators

-0.65

POSITIVE LOGITS

 Rouge

0.68

icket

0.66

 Carlton

0.65

okia

0.65

interrupted

0.63

moil

0.62

atha

0.62

ĺħ

0.60

noticed

0.60

onite

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.