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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iesta

-0.73

lac

-0.63

DeL

-0.62

Í

-0.61

 Koch

-0.61

 caricature

-0.60

 model

-0.60

 Mehran

-0.60

ASA

-0.59

 bloom

-0.59

POSITIVE LOGITS

 Extras

0.85

 Secret

0.71

 Sacrament

0.67

ottesville

0.67

addock

0.66

pelling

0.65

 Sabbath

0.65

SPONSORED

0.65

verage

0.64

checking

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.