INDEX

Explanations

plural nouns, particularly in a possessive form

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

ending in "s"

np_acts-logits-general · gemini-2.0-flash

possessive 's' followed by nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

المناصب

-1.12

ConstraintMaker

-1.02

 autorytatywna

-0.96

 AssemblyTitle

-0.84

 ThemeData

-0.79

 للاسماء

-0.79

 auffi

-0.76

SequentialGroup

-0.75

setVerticalGroup

-0.74

InitVars

-0.73

POSITIVE LOGITS

Own

0.53

dans

0.52

son

0.49

ensä

0.48

 been

0.48

Law

0.47

 latest

0.47

 Place

0.47

 Irish

0.44

 original

0.44

Activations Density 0.127%

plural nouns, particularly in a possessive form

ending in "s"

possessive 's' followed by nouns

No Comments

No Known Activations