INDEX

Explanations

descriptive adjectives and phrases that convey complexity or contradiction

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

ending in "-able", "-ing", or describing landscapes

np_acts-logits-general · gemini-2.0-flash

adjectives describing a noun

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-1.09

tagHelperRunner

-1.05

 propOrder

-0.95

verwijspagina

-0.84

Personensuche

-0.84

 ModelExpression

-0.83

SuppressMessage

-0.83

Hentet

-0.83

 ISNI

-0.81

 surla

-0.80

POSITIVE LOGITS

(!)

0.65

(?)

0.61

(?)

0.60

(!)

0.60

izable

0.57

таки

0.54

isable

0.54

orszá

0.53

ycznie

0.51

følgelig

0.49

Activations Density 0.831%

descriptive adjectives and phrases that convey complexity or contradiction

ending in "-able", "-ing", or describing landscapes

adjectives describing a noun

No Comments

No Known Activations