INDEX

Explanations

programming syntax and structure, particularly related to function definitions and manipulations

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

starting, zero, or minimum values

np_acts-logits-general · gemini-2.0-flash

zero or start

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

tagHelperRunner

-0.69

 saites

-0.69

++

-0.64

 autorytatywna

-0.61

 فريبيس

-0.61

 мәкал

-0.60

 BoxFit

-0.60

 Spisak

-0.58

 upstairs

-0.58

 समीक्षक

-0.57

POSITIVE LOGITS

 zero

1.02

 start

0.94

 starting

0.90

 Zero

0.88

zero

0.86

Zero

0.85

 beginning

0.85

 Start

0.84

Start

0.83

 Beginning

0.83

Activations Density 0.603%

programming syntax and structure, particularly related to function definitions and manipulations

starting, zero, or minimum values

zero or start

No Comments

No Known Activations