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

Ga

-0.71

"},"

-0.65

accept

-0.62

Philipp

-0.62

egg

-0.61

CNN

-0.61

ourke

-0.59

peria

-0.59

abortion

-0.59

laughs

-0.59

POSITIVE LOGITS

ooter

0.74

ttle

0.72

aiden

0.69

ATURE

0.69

 Shard

0.63

 Bear

0.63

 Move

0.63

 span

0.62

 Laurie

0.62

 Starts

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.