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

isma

-0.85

iquette

-0.75

ãģĨ

-0.69

ĨĴ

-0.69

veland

-0.67

igure

-0.67

è»

-0.66

idi

-0.66

Jump

-0.65

thood

-0.64

POSITIVE LOGITS

Nex

0.72

 Sack

0.69

 Afric

0.65

 slash

0.64

0.63

 Sole

0.63

exclusive

0.59

 hash

0.59

ear

0.58

Clo

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.