INDEX

Explanations

references to notable individuals and their achievements

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

preceding names

np_acts-logits-general · gemini-2.0-flash

former associated with titles

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

extAlignment

-0.67

 Aline

-0.62

[]:

-0.61

 indisponible

-0.60

WindowConstants

-0.59

viewDidLoad

-0.58

wußt

-0.58

RenderAtEndOf

-0.58

 Margot

-0.57

@"/

-0.56

POSITIVE LOGITS

 emeritus

0.79

 Emeritus

0.68

 extraordinaire

0.68

 Professor

0.65

 himſelf

0.63

 former

0.60

 veteran

0.60

 sesama

0.59

 malheureux

0.59

Demikian

0.59

Activations Density 0.372%

references to notable individuals and their achievements

preceding names

former associated with titles

No Comments

No Known Activations