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

 compr

-0.81

axter

-0.80

growth

-0.77

aeda

-0.70

atto

-0.70

agall

-0.68

ĸļ

-0.67

lease

-0.65

ioned

-0.64

 Baxter

-0.64

POSITIVE LOGITS

tering

0.90

ters

0.74

##

0.69

offs

0.69

tle

0.69

 Lionel

0.68

Var

0.67

eros

0.67

TX

0.67

TER

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.