INDEX

Explanations

mathematical notation and formatting

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

Subscripts and sets within mathematical expressions

np_acts-logits-general · gemini-2.0-flash

set notation with variables

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

úcar

-0.61

 transfieras

-0.59

TintMode

-0.58

osex

-0.57

tagext

-0.57

مصادر

-0.56

 initComponents

-0.55

 tegas

-0.55

unanje

-0.55

ाहरण

-0.54

POSITIVE LOGITS

memberof

0.53

assertj

0.52

 avoit

0.48

aarrggbb

0.48

kräf

0.46

 pecuni

0.45

mrow

0.44

الإنجليزية

0.44

 Dimensiones

0.44

dza

0.44

Activations Density 0.402%

mathematical notation and formatting

Subscripts and sets within mathematical expressions

set notation with variables

No Comments

No Known Activations