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

hend

-0.74

endiary

-0.74

heng

-0.73

ailability

-0.71

agher

-0.67

artisan

-0.67

raint

-0.67

rang

-0.66

 dism

-0.64

ategory

-0.64

POSITIVE LOGITS

{"

0.73

 volume

0.72

Volume

0.70

icio

0.69

[(

0.68

Lat

0.65

ciating

0.64

 sher

0.64

ãĥ´

0.63

 Dian

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.