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

agos

-0.94

interstitial

-0.88

catentry

-0.80

aucuses

-0.77

pling

-0.73

atican

-0.72

ebook

-0.70

 Huckabee

-0.66

ussions

-0.66

ages

-0.65

POSITIVE LOGITS

Nat

0.67

coe

0.64

 decorated

0.60

ãĤ¯

0.60

 replicated

0.60

 Unch

0.60

armed

0.60

 replicate

0.60

 Insp

0.59

Nam

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.