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

ÄŁ

-0.77

ÅŁ

-0.72

abies

-0.68

our

-0.65

ours

-0.61

cling

-0.61

hya

-0.61

acas

-0.60

 fees

-0.59

seek

-0.58

POSITIVE LOGITS

\\\\

0.88

éĹĺ

0.82

»Ĵ

0.81

à¼

0.79

\\\\\\\\

0.78

 Collider

0.77

ĸļ

0.74

soDeliveryDate

0.72

clave

0.72

Magikarp

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.