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

 distilled

-0.74

estamp

-0.73

unts

-0.71

 antid

-0.68

 fermented

-0.67

 rall

-0.66

 abort

-0.66

 downstream

-0.65

ined

-0.65

Ã¶

-0.64

POSITIVE LOGITS

UGH

0.81

 SHALL

0.74

 Areas

0.73

"]=>

0.68

":["

0.67

<?

0.66

wikipedia

0.66

ONES

0.66

:]

0.65

 Especially

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.