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

LF

-0.66

-0.63

 scene

-0.63

 revol

-0.61

 Craigslist

-0.60

-0.59

 website

-0.59

trade

-0.59

bsite

-0.58

tube

-0.58

POSITIVE LOGITS

×©

0.81

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.76

++++++++

0.75

Ô

0.74

isance

0.74

heit

0.72

teness

0.70

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.69

ipal

0.68

Î¹

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.