INDEX

Explanations

references to specific films, actors, and film-related awards

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

Followed by "was"

np_acts-logits-general · gemini-2.0-flash

general relativity states

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

-0.78

 surla

-0.77

 kasarigan

-0.76

 jScrollPane

-0.70

SEGUIR

-0.69

--*/

-0.67

qrstuvwxyz

-0.67

+#+#

-0.65

 ModelExpression

-0.63

]")]

-0.62

POSITIVE LOGITS

 Olympedia

0.54

 sociaux

0.49

cyklo

0.48

RTEE

0.45

keyColumn

0.44

 altrett

0.43

 proprement

0.42

 Geraadpleegd

0.42

 auxquels

0.41

Carreira

0.41

Activations Density 1.575%

references to specific films, actors, and film-related awards

Followed by "was"

general relativity states

No Comments

No Known Activations