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

ANE

-0.67

ird

-0.65

 mathemat

-0.63

IDs

-0.63

UF

-0.60

ARM

-0.59

WA

-0.59

DK

-0.59

UGH

-0.59

zu

-0.57

POSITIVE LOGITS

the

1.14

0.96

its

0.84

an

0.82

 this

0.80

his

0.77

our

0.74

 another

0.68

hower

0.67

 what

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.