INDEX

Explanations

technical terms and phrases related to coding and programming constructs

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

Preceding ordinal numbers or capitalized words

np_acts-logits-general · gemini-2.0-flash

adjective describing a noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ientôt

-0.51

 jagung

-0.48

 Sachen

-0.45

 perfeita

-0.44

 Vereine

-0.44

 Autorin

-0.42

 Ärz

-0.41

 Verhältnisse

-0.41

 czę

-0.41

 raça

-0.40

POSITIVE LOGITS

 MatDialog

0.61

Ārējās

0.61

abetes

0.55

 ſch

0.54

 ſche

0.54

Maf

0.52

 ThemeData

0.52

 дописавши

0.51

 betweenstory

0.51

 للمعارف

0.49

Activations Density 1.937%

technical terms and phrases related to coding and programming constructs

Preceding ordinal numbers or capitalized words

adjective describing a noun

No Comments

No Known Activations