INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

jri

-0.79

iferation

-0.75

çļ

-0.71

orescence

-0.70

Pont

-0.70

ogle

-0.69

âĹ¼

-0.68

Commun

-0.65

è¦ļéĨĴ

-0.65

 behavi

-0.64

POSITIVE LOGITS

wikipedia

0.74

 Favor

0.72

 SHARES

0.71

ettings

0.64

 Beats

0.62

itiz

0.60

 Survivor

0.60

 Sixers

0.59

 Curse

0.59

\'

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.