INDEX

Explanations

technical terms related to web browser errors and debugging information

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

web browsers or web development

np_acts-logits-general · gemini-2.0-flash

web browser components

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

 better

-0.71

 mejor

-0.64

better

-0.62

 besser

-0.61

 mieux

-0.58

 melhor

-0.57

 brief

-0.55

 Brief

-0.53

 briefly

-0.53

brief

-0.53

POSITIVE LOGITS

 Chrome

0.84

 chrome

0.78

Datuak

0.75

 chromium

0.74

 Chromium

0.73

ChromeDriver

0.72

chrome

0.72

Chrome

0.72

 firefox

0.72

chromium

0.70

Activations Density 0.248%

technical terms related to web browser errors and debugging information

web browsers or web development

web browser components

No Comments

No Known Activations