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

>[

-0.87

)</

-0.82

Engineers

-0.76

VK

-0.74

icago

-0.71

 corrid

-0.70

SPONSORED

-0.67

 Entered

-0.66

votes

-0.65

DERR

-0.65

POSITIVE LOGITS

pir

0.77

incarn

0.69

posing

0.68

ciples

0.67

ients

0.64

ivation

0.64

poses

0.64

inger

0.63

iences

0.63

plets

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.