INDEX

Explanations

references to notable individuals and their roles or titles

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

Appears before a title or role

np_acts-logits-general · gemini-2.0-flash

roles and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ьаж

-0.71

setArguments

-0.59

 BoxDecoration

-0.58

 betweenstory

-0.56

 estimés

-0.56

作為

-0.55

richTextPanel

-0.51

EClass

-0.51

livé

-0.50

 pamamagitan

-0.50

POSITIVE LOGITS

 only

0.63

 youngest

0.62

 founder

0.62

 encargado

0.60

 chief

0.59

 oldest

0.58

 head

0.58

 lead

0.58

 sole

0.56

 owner

0.56

Activations Density 0.173%

references to notable individuals and their roles or titles

Appears before a title or role

roles and positions

No Comments

No Known Activations