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

 credentials

-0.71

 destro

-0.65

İĭ

-0.63

ael

-0.61

 proves

-0.59

 practitioner

-0.59

ITH

-0.58

 excludes

-0.58

 promot

-0.57

 Roots

-0.57

POSITIVE LOGITS

ellar

0.71

lined

0.68

gallery

0.68

ublic

0.66

 Resp

0.66

 scanner

0.65

scan

0.64

artments

0.63

artment

0.63

 Telesc

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.