INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Seah

-0.79

 Brach

-0.76

 Nieto

-0.75

 Weaver

-0.73

wreck

-0.68

PP

-0.68

Sev

-0.68

 Aval

-0.67

 Palest

-0.67

 Ramos

-0.66

POSITIVE LOGITS

emetery

0.71

 cutoff

0.66

gal

0.65

 closures

0.62

veyard

0.62

iblings

0.61

 setbacks

0.61

tein

0.60

things

0.60

anguage

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.