INDEX

Explanations

instances of choice-related terminology

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

Follows punctuation or common words

np_acts-logits-general · gemini-2.0-flash

Q: followed by text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 purpoſe

-0.78

 ſch

-0.78

 perſon

-0.77

 eſt

-0.74

 ſol

-0.73

 Diſ

-0.71

 cauſe

-0.70

 ſta

-0.70

 juſ

-0.70

 ſen

-0.69

POSITIVE LOGITS

 unknownFields

0.68

PageModule

0.62

 Wikispecies

0.60

 <>",

0.59

 նաև

0.56

oredCriteria

0.56

Πηγές

0.55

 kanssa

0.55

 AppModule

0.55

getSystemService

0.54

Activations Density 0.646%

instances of choice-related terminology

Follows punctuation or common words

Q: followed by text

No Comments

No Known Activations