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

 sweats

-0.78

 Wester

-0.67

 belts

-0.66

 belt

-0.65

 personalities

-0.63

 tast

-0.63

Kry

-0.62

 conco

-0.61

 Sask

-0.61

 toast

-0.60

POSITIVE LOGITS

parser

0.71

 Cantor

0.70

finder

0.69

itely

0.69

OTO

0.69

udi

0.68

]:

0.67

ktop

0.66

xp

0.65

eret

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.