INDEX

Explanations

mathematical and programming notations related to equations and structures in scientific contexts

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

Code, especially related to math, logic, or physics

np_acts-logits-general · gemini-2.0-flash

`self` followed by `calibration`, `ass` followed by `umed`

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 المعيارى

-0.71

 ivelany

-0.69

 GENERATED

-0.64

 auprès

-0.60

AutoField

-0.60

Enllaces

-0.59

Trama

-0.58

 Rigidbody

-0.58

 muualla

-0.58

 Normdatei

-0.57

POSITIVE LOGITS

getDoctrine

0.58

createClass

0.54

RenderAtEndOf

0.54

CellStyle

0.53

AndEndTag

0.51

oplasty

0.49

icitis

0.49

bourhood

0.48

FunctionFlags

0.47

 Initial

0.46

Activations Density 1.297%

mathematical and programming notations related to equations and structures in scientific contexts

Code, especially related to math, logic, or physics

`self` followed by `calibration`, `ass` followed by `umed`

No Comments

No Known Activations