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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erion

-0.82

ether

-0.79

intend

-0.69

egu

-0.68

GoldMagikarp

-0.65

course

-0.65

amphetamine

-0.65

iction

-0.65

 adoption

-0.64

hetamine

-0.64

POSITIVE LOGITS

 Skies

0.70

Roz

0.70

 Quote

0.69

 Tyrann

0.67

 Democr

0.67

hawk

0.64

Laf

0.63

Hue

0.61

 attRot

0.61

Maz

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.