INDEX

Explanations

ordinal indicators and enumerations

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

the ordinal number first

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

miljø

-0.55

magitan

-0.54

 henvisninger

-0.51

 sobremesa

-0.48

 veckan

-0.48

 cafetería

-0.47

depuis

-0.47

 rodilla

-0.46

RefNanny

-0.46

 montanha

-0.46

POSITIVE LOGITS

 First

0.83

 first

0.77

First

0.74

 FIRST

0.71

first

0.69

FIRST

0.66

 firft

0.62

 nahilalakip

0.59

 firs

0.59

Первый

0.59

Activations Density 0.006%

ordinal indicators and enumerations

the ordinal number first

No Comments

No Known Activations

ordinal indicators and enumerations

the ordinal number first

No Comments

No Known Activations