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

itory

-0.70

responsive

-0.68

hyde

-0.68

pathy

-0.66

acco

-0.66

advertisement

-0.65

STDOUT

-0.64

izabeth

-0.64

apps

-0.63

bourg

-0.62

POSITIVE LOGITS

pload

0.81

²¾

0.78

ģĸ

0.70

 Forward

0.70

orld

0.70

ÃĥÃĤ

0.68

ÑĢ

0.68

Ð»

0.66

¢

0.66

¥

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.