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

ariat

-0.84

mosp

-0.73

includes

-0.64

 Material

-0.64

ATURE

-0.63

 Tables

-0.63

IGH

-0.63

 WARN

-0.62

 Chrysler

-0.60

raph

-0.59

POSITIVE LOGITS

 congr

0.76

nesty

0.69

ichick

0.68

 surn

0.67

hes

0.66

 appe

0.64

 impunity

0.64

 incrim

0.64

 confisc

0.63

 thanking

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.