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

ulton

-0.75

hips

-0.66

 Dayton

-0.66

icons

-0.64

loading

-0.64

ppings

-0.64

Ap

-0.64

ILE

-0.63

 Loading

-0.63

ĨĴ

-0.63

POSITIVE LOGITS

umbnails

0.79

self

0.68

ufact

0.68

 pains

0.68

ELF

0.68

ModLoader

0.67

ittee

0.67

unes

0.65

 Citiz

0.64

uary

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.