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

¬¼

-0.74

cknow

-0.71

cation

-0.70

 unlaw

-0.69

 contingency

-0.68

vet

-0.68

Vet

-0.66

OPLE

-0.62

ignt

-0.62

 Echo

-0.61

POSITIVE LOGITS

xon

0.84

nature

0.76

poon

0.74

chin

0.68

olf

0.67

----------

0.65

hes

0.65

ouls

0.65

çīĪ

0.64

alloc

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.