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

otype

-0.83

idas

-0.70

eli

-0.69

otypes

-0.68

emetery

-0.65

phal

-0.65

orned

-0.64

ocol

-0.64

Tumblr

-0.63

ihara

-0.63

POSITIVE LOGITS

 produ

0.71

\-

0.69

administ

0.65

VERTISEMENT

0.65

pse

0.64

 âĢİ

0.62

 webs

0.61

adelphia

0.61

ionage

0.60

 answ

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.