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

rypt

-0.83

late

-0.80

olly

-0.75

roph

-0.72

hy

-0.71

gging

-0.68

gged

-0.67

È

-0.67

velt

-0.64

beta

-0.64

POSITIVE LOGITS

Times

0.69

-+-+

0.69

agher

0.66

 Sweeney

0.64

 certific

0.64

 Slater

0.62

borough

0.62

 gist

0.61

 laun

0.60

 appell

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.