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

luaj

-0.73

Untitled

-0.66

moil

-0.65

chev

-0.64

Mal

-0.64

Discuss

-0.64

heading

-0.63

\">

-0.63

Ca

-0.62

nton

-0.62

POSITIVE LOGITS

 Edison

0.65

 Parenthood

0.65

ivari

0.63

issions

0.62

 mornings

0.62

 waivers

0.61

dab

0.61

akes

0.61

 Disciple

0.61

steen

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.