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

 bronze

-0.76

inct

-0.67

along

-0.61

holder

-0.60

 bidder

-0.59

 Authent

-0.59

ahon

-0.58

 resonance

-0.57

agara

-0.57

 inscription

-0.57

POSITIVE LOGITS

 Murd

0.72

 Slaughter

0.71

prime

0.70

 Continent

0.70

ategory

0.69

ãĤ¡

0.68

ozy

0.67

 ---------

0.66

 Spiegel

0.64

 Dunk

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.