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

uden

-0.71

 OLED

-0.68

 DRAG

-0.67

 Database

-0.64

pmwiki

-0.63

 resize

-0.62

 eclipse

-0.62

"]=>

-0.62

ROM

-0.62

 namespace

-0.60

POSITIVE LOGITS

raught

0.74

anguage

0.73

antage

0.71

iger

0.70

iste

0.69

agers

0.69

airy

0.69

lain

0.68

wegian

0.68

helm

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.