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

iously

-0.69

 Starg

-0.67

innacle

-0.65

 designation

-0.64

 heartbeat

-0.63

 Grade

-0.63

 identifier

-0.60

 cellar

-0.60

geist

-0.60

 stockpile

-0.59

POSITIVE LOGITS

raq

0.82

ternity

0.81

³

0.81

skirts

0.79

packs

0.76

naire

0.75

 lawy

0.72

Ago

0.70

alde

0.68

anson

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.