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

 gearing

-0.72

liga

-0.72

wards

-0.69

 Byrd

-0.60

rosse

-0.60

AW

-0.58

camp

-0.58

 awoken

-0.57

hawk

-0.57

POSITIVE LOGITS

omorphic

0.70

isoft

0.68

inite

0.68

rant

0.63

onic

0.62

udden

0.61

icious

0.61

NT

0.61

ERT

0.59

avorable

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.