INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Shell

-0.72

Scient

-0.70

Correct

-0.69

 Clown

-0.68

)].

-0.66

amus

-0.66

inic

-0.66

 Shell

-0.66

âĵĺ

-0.64

âĢ²

-0.64

POSITIVE LOGITS

oleon

0.71

atche

0.69

 wardrobe

0.68

cipled

0.67

¬¼

0.66

akura

0.65

loe

0.63

aldi

0.59

 volunt

0.59

edy

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.