INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 fools

-0.66

 Ambrose

-0.62

 Chamberlain

-0.61

icut

-0.60

 vans

-0.60

 slap

-0.58

 Reneg

-0.58

sted

-0.58

 permits

-0.58

 Correct

-0.58

POSITIVE LOGITS

ãĥ´

0.86

esan

0.75

ITAL

0.73

ãĥĺ

0.71

Sales

0.70

uberty

0.66

Char

0.66

gui

0.66

oir

0.64

iHUD

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.