INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Annotations

-0.84

pec

-0.79

TAG

-0.77

ERC

-0.75

ngth

-0.72

IME

-0.70

FIELD

-0.69

pload

-0.66

CRIP

-0.66

 Offer

-0.66

POSITIVE LOGITS

itaire

0.78

zona

0.73

acci

0.70

itatively

0.69

 Brill

0.67

ttle

0.65

 Pierce

0.64

ãĥĦ

0.64

igating

0.63

 Patton

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.