INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

atto

-0.86

uckland

-0.78

Corp

-0.76

LV

-0.74

EStream

-0.71

atl

-0.70

common

-0.68

merce

-0.67

aspers

-0.66

``

-0.64

POSITIVE LOGITS

 accents

0.68

 terms

0.66

 reporting

0.66

arthed

0.60

 unfounded

0.59

 spac

0.59

Sud

0.58

 speaking

0.57

 melt

0.56

 Shin

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.