INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

pha

-0.71

ranged

-0.70

thia

-0.64

rio

-0.64

SpaceEngineers

-0.63

PsyNetMessage

-0.61

 è£ıç

-0.61

urtle

-0.61

otal

-0.61

vol

-0.61

POSITIVE LOGITS

conom

0.78

mere

0.66

illin

0.66

+++

0.66

 Finder

0.65

VERTISEMENT

0.64

CTV

0.62

ients

0.61

:]

0.61

ucker

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.