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

lain

-0.70

glas

-0.69

HI

-0.68

âķĲ

-0.68

DN

-0.66

HUD

-0.65

ymm

-0.65

Advertisements

-0.63

DOWN

-0.61

factor

-0.59

POSITIVE LOGITS

 Sind

0.72

 survival

0.71

 lifes

0.67

 Sabha

0.66

rist

0.66

 puzz

0.65

Activ

0.64

 queues

0.63

fal

0.62

lif

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.