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

 dependence

-0.74

ufact

-0.73

 solder

-0.71

 equival

-0.67

 schemes

-0.64

 stru

-0.63

orsche

-0.62

ogly

-0.62

amins

-0.61

 drafts

-0.61

POSITIVE LOGITS

igne

0.80

Gov

0.79

steen

0.72

udic

0.71

lund

0.71

 Beir

0.68

indal

0.67

opian

0.66

ANCE

0.66

oner

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.