INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 æľ

-0.66

ibling

-0.65

ailability

-0.64

 Birthday

-0.64

ãĤ¦ãĤ¹

-0.64

pie

-0.61

 attic

-0.59

 vending

-0.59

 icing

-0.59

 unex

-0.58

POSITIVE LOGITS

ription

0.73

GW

0.70

tein

0.70

nor

0.66

agna

0.66

raltar

0.65

KR

0.65

kick

0.65

 Nicholson

0.64

yssey

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.