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

 Guant

-0.70

behind

-0.66

 Tracking

-0.64

 Obst

-0.64

"],"

-0.62

Jaw

-0.60

 Compass

-0.60

 Vertical

-0.58

 Privacy

-0.57

oped

-0.57

POSITIVE LOGITS

 Ukrain

0.87

 millenn

0.82

 enthusi

0.78

 indo

0.78

arnaev

0.77

 tremend

0.75

 fortun

0.75

henko

0.75

rue

0.75

ModLoader

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.