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

Child

-0.80

 Franchise

-0.71

Person

-0.70

Tal

-0.70

Senator

-0.70

swick

-0.69

Ax

-0.67

Govern

-0.67

 Moody

-0.66

Kids

-0.66

POSITIVE LOGITS

eme

0.68

veyard

0.68

 combustion

0.65

izon

0.63

 surf

0.63

arettes

0.63

 sighting

0.61

ouston

0.61

etta

0.61

 intakes

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.