INDEX

Explanations

mathematical symbols and formatting related to equations and expressions

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

Mathematical notation related to variables

np_acts-logits-general · gemini-2.0-flash

lambda with indices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

CloseOperation

-0.40

ungsver

-0.38

 ungkapnya

-0.36

randomUUID

-0.36

ung

-0.36

shot

-0.36

határoz

-0.36

grund

-0.35

Doc

-0.35

intervention

-0.35

POSITIVE LOGITS

AndEndTag

0.62

 חיצוניים

0.57

 ISNI

0.54

__*/

0.54



0.52

 snippetHide

0.51

colhead

0.51

Tembelea

0.51

BASEPATH

0.50

 AssemblyCompany

0.50

Activations Density 1.145%

mathematical symbols and formatting related to equations and expressions

Mathematical notation related to variables

lambda with indices

No Comments

No Known Activations