INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

paren

-0.75

 ILCS

-0.71

anned

-0.68

Downloadha

-0.67

 plur

-0.66

 pron

-0.64

 pitched

-0.64

 transitions

-0.64

olson

-0.63

 lawsuits

-0.63

POSITIVE LOGITS

issance

0.71

Crash

0.68

vy

0.67

Hash

0.67

 istg

0.65

Task

0.64

Topics

0.63

zo

0.63

othal

0.63

Maw

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.