INDEX

Explanations

references to physical appearance and descriptive attributes

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

Non-English words or code snippets

np_acts-logits-general · gemini-2.0-flash

list entries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

govina

-0.59

::::::::

-0.56

 humaine

-0.54

 lourdes

-0.54

 privato

-0.52

 éste

-0.52

onAttach

-0.52

_('

-0.52

numberOfLines

-0.52

yordu

-0.51

POSITIVE LOGITS

 виправивши

0.63

эффици

0.56

struzioni

0.53

 ویکی‌پدیای

0.53

 *)__

0.52

lip

0.50

--){

0.49

]})

0.49

'>{

0.49

 '\\;'

0.48

Activations Density 0.043%

references to physical appearance and descriptive attributes

Non-English words or code snippets

list entries

No Comments

No Known Activations