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

 captcha

-0.65

ĸļ

-0.65

 portals

-0.63

 psychiat

-0.62

CCP

-0.62

 blockers

-0.60

 Cyborg

-0.59

 Chandra

-0.59

 answering

-0.58

upload

-0.58

POSITIVE LOGITS

anyahu

0.72

unts

0.70

ordinate

0.68

uchin

0.65

 tailor

0.65

lass

0.63

herer

0.62

zbollah

0.62

 Whitman

0.61

tle

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.