INDEX

Explanations

syntax-related terms and structures in code or programming language constructs

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

Lisp-like syntax and/or math expressions

np_acts-logits-general · gemini-2.0-flash

arrows (`->`) and labels

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Frid

-0.55

 perio

-0.52

 dotenv

-0.51

 Estim

-0.47

ProcessEvent

-0.46

ResumeLayout

-0.46

SerializedName

-0.45

 trend

-0.42

 handker

-0.42

 gants

-0.42

POSITIVE LOGITS

 للاسماء

0.77

 Normdatei

0.72

MessageTagHelper

0.70

 autorytatywna

0.70

 تضيفلها

0.68

 utafitiHapana

0.67

RenderAtEndOf

0.65

çoise

0.64

odeon

0.64

حياتها

0.63

Activations Density 1.309%

syntax-related terms and structures in code or programming language constructs

Lisp-like syntax and/or math expressions

arrows (`->`) and labels

No Comments

No Known Activations