INDEX

Explanations

technical terms and expressions related to inventions and their detailed descriptions in documentation

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

Figures or diagrams with labels

np_acts-logits-general · gemini-2.0-flash

figure views and diagrams

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

 CreateTagHelper

-1.06

verwijspagina

-0.91

 doInBackground

-0.87

évaluateur

-0.82

VideoCapture

-0.81

+:+

-0.79

 Normdatei

-0.75

medriver

-0.72

SBATCH

-0.69

TabIndex

-0.68

POSITIVE LOGITS

 view

1.32

 schematic

1.10

view

1.07

 View

1.06

 views

0.97

Schematic

0.96

View

0.95

 VIEW

0.94

 diagram

0.92

 detail

0.91

Activations Density 0.736%

technical terms and expressions related to inventions and their detailed descriptions in documentation

Figures or diagrams with labels

figure views and diagrams

No Comments

No Known Activations