INDEX

Explanations

references to governmental and institutional structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 itſelf

-0.78

 CreateTagHelper

-0.77

 Administrativna

-0.76

 שוליים

-0.75

 Monfieur

-0.75

 myſelf

-0.74

 purpoſe

-0.73

 nahilalakip

-0.73

 Jefus

-0.72

 Italij

-0.72

POSITIVE LOGITS

vs

0.53

pas

0.48

 createContext

0.41

 versus

0.40

ís

0.39

nas

0.38

lo

0.38

don

0.38

vs

0.37

Activations Density 0.989%

references to governmental and institutional structures

No Comments

No Known Activations