INDEX

Explanations

the term "central" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MSA

-0.78

 Indore

-0.76

 Roskov

-0.76

NDA

-0.76

 josh

-0.75

 pittura

-0.74

 ModelExpression

-0.73

 inglesa

-0.73

 skimage

-0.73

 boire

-0.73

POSITIVE LOGITS

 Central

0.95

Central

0.86

 central

0.83

isation

0.83

central

0.82

 CENTRAL

0.79

ized

0.77

CENTRAL

0.74

alised

0.72

Datuak

0.72

Activations Density 0.057%

the term "central" in various contexts

No Comments

No Known Activations