INDEX

Explanations

statistical symbols and formatting used in academic writing

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

Character after parentheses, brackets, or colons

np_acts-logits-general · gemini-2.0-flash

citations with numbers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

writeField

-0.59

Portály

-0.58

󠁢

-0.55

 оригіналу

-0.53

 للمعارف

-0.53

expandindo

-0.52

ಾನ

-0.48

tvguidetime

-0.47

CppMethod

-0.47

Gweler

-0.47

POSITIVE LOGITS

 disambiguazione

0.57

$}}

0.56

ositol

0.56

"])

0.55

 quartzite

0.55

tonode

0.53

 Mathilde

0.53

 Faire

0.53

 betweenstory

0.52

 Lancelot

0.52

Activations Density 0.170%

statistical symbols and formatting used in academic writing

Character after parentheses, brackets, or colons

citations with numbers

No Comments

No Known Activations