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

beck

-0.76

hett

-0.71

ersed

-0.71

hands

-0.69

 Cats

-0.67

 SERV

-0.64

 rehears

-0.63

 Dancing

-0.62

 waivers

-0.62

rist

-0.62

POSITIVE LOGITS

 opium

0.73

 undert

0.68

 impe

0.67

amina

0.65

rawdownloadcloneembedreportprint

0.63

itans

0.63

 Vietnamese

0.62

 conditioned

0.61

intend

0.61

ijing

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.