INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

reens

-0.67

WD

-0.65

qua

-0.64

trap

-0.63

AME

-0.63

RM

-0.62

nu

-0.62

iour

-0.61

existent

-0.60

BILITIES

-0.60

POSITIVE LOGITS

notations

0.71

instein

0.68

 corpus

0.66

 Insider

0.65

igue

0.64

otted

0.63

 crowds

0.62

isse

0.62

owsky

0.62

otin

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.