INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Destination

-0.72

 Fargo

-0.69

Bench

-0.68

 Goddard

-0.67

 Fairfax

-0.65

reau

-0.65

dst

-0.62

 disproportion

-0.62

MTA

-0.61

 Hastings

-0.61

POSITIVE LOGITS

 VIDEOS

0.73

uminati

0.68

icle

0.65

ousse

0.64

 weeds

0.63

ocy

0.63

udic

0.62

natureconservancy

0.61

 organise

0.61

ivated

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.