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

headed

-0.72

antha

-0.69

è¦ļéĨĴ

-0.67

ngth

-0.64

enfranch

-0.64

htt

-0.64

 tatt

-0.61

é¾įå

-0.61

orr

-0.60

OSE

-0.60

POSITIVE LOGITS

 Simulator

0.76

Style

0.64

)</

0.63

 simulator

0.61

ieu

0.61

Guide

0.61

index

0.61

ies

0.61

}}

0.61

ido

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.