INDEX

Explanations

mathematical variables and their relationships within equations

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

Letters in parentheses

np_acts-logits-general · gemini-2.0-flash

names and acronyms

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

 насељу

-0.51

 perak

-0.50

Географиясе

-0.45

Gambas

-0.45

drawiam

-0.44

linspace

-0.44

yors

-0.44

PAREN

-0.44

DropTable

-0.43

 dachte

-0.43

POSITIVE LOGITS

contentLoaded

0.70

NameInMap

0.69

parsedMessage

0.67

InstrumentedTest

0.54

CCCC

0.53

ClientSize

0.52

 canvas

0.52

ReusableCell

0.52

 Christen

0.51

 Canvas

0.51

Activations Density 0.338%

mathematical variables and their relationships within equations

Letters in parentheses

names and acronyms

No Comments

No Known Activations