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

opic

-0.60

HP

-0.60

Todd

-0.59

Kad

-0.58

 debian

-0.58

 distraction

-0.58

umers

-0.58

Percent

-0.58

ylan

-0.57

idal

-0.57

POSITIVE LOGITS

 tiss

0.74

ãĤ¨ãĥ«

0.71

ilitary

0.70

aughs

0.68

eatures

0.68

forth

0.66

angered

0.64

merce

0.64

è¦ļéĨĴ

0.63

æĸ¹

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.