INDEX

Explanations

references to specific authors or researchers in a scientific context

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

Appears before volume and page numbers

np_acts-logits-general · gemini-2.0-flash

names in citations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

IsContent

-0.76

 EClass

-0.75

]='\

-0.72

ReusableCell

-0.71

AutoScaleMode

-0.70

kloped

-0.68

qrstuvwxyz

-0.67

 ModelExpression

-0.66

 Ressources

-0.65

 muualla

-0.65

POSITIVE LOGITS

Jr

0.50

 estimés

0.47

and

0.45

Przypisy

0.44

 unpublished

0.43

 orally

0.39

 testified

0.39

FirstResponder

0.39

.,

0.39

Activations Density 0.244%

references to specific authors or researchers in a scientific context

Appears before volume and page numbers

names in citations

No Comments

No Known Activations