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

î

-0.91

 VIDEOS

-0.87

AMI

-0.69

 ILCS

-0.66

aint

-0.62

quished

-0.62

çĲ

-0.61

 stimulus

-0.61

Sav

-0.60

 Ambro

-0.59

POSITIVE LOGITS

adobe

0.74

clave

0.68

]+

0.66

abama

0.65

bay

0.65

aden

0.61

mobi

0.60

aird

0.58

_>

0.58

 Panda

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.