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

ItemImage

-0.73

 secretaries

-0.70

pins

-0.68

 revelation

-0.68

skirts

-0.67

 penetration

-0.66

 appointment

-0.66

µ

-0.66

street

-0.65

 sunscreen

-0.63

POSITIVE LOGITS

oother

0.85

artney

0.84

uve

0.79

itual

0.77

âĶĢâĶĢâĶĢâĶĢ

0.73

iversal

0.73

essel

0.71

vant

0.69

 Ambro

0.69

ajor

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.