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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Kut

-0.70

 Holo

-0.69

wic

-0.68

iyah

-0.68

 Browse

-0.68

 Greenland

-0.67

wom

-0.67

ãĤ£

-0.64

 Universities

-0.63

Spo

-0.63

POSITIVE LOGITS

osuke

0.71

brance

0.70

oleon

0.66

 hereby

0.66

alia

0.64

bered

0.64

ricks

0.64

zynski

0.63

 resorted

0.61

ased

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.