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

asca

-0.74

urdy

-0.73

 Riders

-0.72

ibaba

-0.71

estern

-0.71

onga

-0.71

vern

-0.71

eman

-0.68

Tut

-0.67

ldon

-0.67

POSITIVE LOGITS

 equally

0.69

need

0.67

times

0.66

Month

0.64

gerald

0.62

SPONSORED

0.62

 understatement

0.62

aples

0.62

Putin

0.62

JUST

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.