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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

berus

-0.76

itent

-0.67

obic

-0.65

 blessings

-0.65

ammad

-0.64

apeshifter

-0.64

itsch

-0.63

ubb

-0.62

oola

-0.62

lah

-0.61

POSITIVE LOGITS

 Skydragon

0.81

ĸļ

0.76

©¶æ¥µ

0.76

 Measures

0.69

¬¼

0.68

 Binding

0.67

 Sack

0.66

correct

0.65

absolute

0.64

 Cars

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.