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

Ada

-0.71

TT

-0.67

UL

-0.64

 Borg

-0.63

MOT

-0.62

PID

-0.62

 motors

-0.62

 Ducks

-0.62

 mirrors

-0.61

 Autism

-0.60

POSITIVE LOGITS

ãģ®éŃĶ

0.86

uper

0.80

cum

0.80

»

0.80

©¶æ

0.78

ince

0.78

º

0.77

Ń·

0.75

ä»£

0.74

pie

0.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.