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

ample

-0.63

eed

-0.62

ential

-0.61

 entitlement

-0.61

)]

-0.60

ee

-0.60

pling

-0.60

bledon

-0.59

pled

-0.59

psc

-0.59

POSITIVE LOGITS

ugu

0.71

fy

0.68

kos

0.67

Sty

0.65

odynam

0.64

cult

0.63

dn

0.62

alla

0.61

 Italians

0.60

 masc

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.