INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

itage

-0.82

ricanes

-0.80

wcs

-0.77

metics

-0.72

plet

-0.72

agall

-0.71

 pipeline

-0.69

Û

-0.68

isine

-0.67

zens

-0.67

POSITIVE LOGITS

orem

0.67

Rush

0.66

 Herod

0.63

anu

0.62

HIP

0.62

Ish

0.61

 Married

0.60

 TAMADRA

0.60

 Surviv

0.60

 Hera

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.