INDEX

Explanations

structured or formatted text that conveys specific information, possibly related to scientific or technical contexts

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

Text following "Q:" (likely questions)

np_acts-logits-general · gemini-2.0-flash

non-English words and programming terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Scre

-0.57

尖叫

-0.56

styleable

-0.56

 dAtA

-0.56

eably

-0.56

indale

-0.55

errHandler

-0.54

happily

-0.54

ListItemIcon

-0.53

 happily

-0.53

POSITIVE LOGITS

 chi̍t

0.64

awtextra

0.61

Lähteet

0.60

 propOrder

0.60

artifactId

0.56

 Réponses

0.55

 للاسماء

0.54

 communiquez

0.53

 nakalista

0.52

 vuitton

0.52

Activations Density 0.080%

structured or formatted text that conveys specific information, possibly related to scientific or technical contexts

Text following "Q:" (likely questions)

non-English words and programming terms

No Comments

No Known Activations