INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

otech

-0.68

ragon

-0.66

Wee

-0.66

Æ

-0.66

icably

-0.61

Ja

-0.58

âĢ¢âĢ¢

-0.58

 Heath

-0.57

iland

-0.57

Za

-0.57

POSITIVE LOGITS

 nodd

0.80

 suspic

0.79

 metic

0.76

 millenn

0.72

 compr

0.71

cknow

0.70

 challeng

0.69

alyses

0.69

 veter

0.69

apters

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.