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

estyles

-0.80

 Tang

-0.69

Ups

-0.67

umble

-0.66

utic

-0.62

Ru

-0.62

 Sere

-0.60

iqueness

-0.58

ateral

-0.58

 capacitor

-0.57

POSITIVE LOGITS

alist

0.77

icion

0.77

alian

0.72

Girl

0.70

pex

0.70

hem

0.68

meric

0.68

abase

0.67

atari

0.66

ulhu

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.