INDEX

Explanations

symbols and notations typically used in mathematical expressions and scientific writing

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

latex citations and math expressions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Normdatei

-0.79

 AssemblyCulture

-0.78

tagHelperRunner

-0.66

transQ

-0.64

iſen

-0.64

<unused28>

-0.64

<unused79>

-0.63

 ویکی‌پدی

-0.63

<unused41>

-0.63

<unused8>

-0.63

POSITIVE LOGITS

Dr

0.35

Ma

0.35

Llu

0.35

 Greek

0.35

 Liber

0.34

咯

0.33

 внут

0.33

ex

0.33

 Japanese

0.33

Ex

0.32

Activations Density 0.199%

symbols and notations typically used in mathematical expressions and scientific writing

latex citations and math expressions

No Comments

No Known Activations