INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

apult

-0.92

daq

-0.83

-0.81

ãĥ´

-0.80

cham

-0.79

oliberal

-0.77

ropolis

-0.71

emonic

-0.71

 Asgard

-0.71

emo

-0.68

POSITIVE LOGITS

âĢ

1.14

Interested

0.71

Â¶

0.70

 Sear

0.70

[/

0.69

âĶĢâĶĢ

0.69

 concurrent

0.64

FUL

0.63

meyer

0.61

 Investigative

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.