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

avorite

-0.76

erson

-0.75

properties

-0.74

ertodd

-0.74

 profiles

-0.73

cox

-0.72

gado

-0.71

abba

-0.71

arov

-0.71

asca

-0.70

POSITIVE LOGITS

 Doll

0.69

)\

0.68

DOI

0.66

 tooth

0.65

Fey

0.60

 knockout

0.58

 Dungeons

0.58

 Raid

0.57

pet

0.57

Untitled

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.