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

ÑĮ

-0.76

OPS

-0.68

maxwell

-0.64

 Theme

-0.64

-0.60

ashtra

-0.60

Sut

-0.60

Website

-0.59

OUR

-0.57

 Newsletter

-0.57

POSITIVE LOGITS

ħĭ

0.99

pires

0.94

©¶æ

0.92

pired

0.91

sembly

0.85

cember

0.74

ci

0.72

ipolar

0.71

ointment

0.71

 soon

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.