INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 COUR

-0.84

ificial

-0.83

 Ambro

-0.78

 Atmosp

-0.69

idences

-0.67

AUD

-0.67

bourg

-0.66

utics

-0.66

meyer

-0.66

uberty

-0.64

POSITIVE LOGITS

odan

0.66

 Fighters

0.62

raid

0.60

 Fighter

0.59

errilla

0.59

 preferring

0.58

 Hitman

0.58

ascus

0.57

 checkpoint

0.57

 Saddam

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.