INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

redd

-0.82

 fuzz

-0.72

ĸļ

-0.66

 richness

-0.64

\-

-0.63

 rupture

-0.62

 antioxid

-0.62

 corrid

-0.62

»Ĵ

-0.61

 challeng

-0.61

POSITIVE LOGITS

malink

0.81

VEL

0.69

umn

0.69

ificent

0.67

puters

0.67

 =================================

0.64

NEWS

0.63

ately

0.63

LY

0.62

usions

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.