INDEX

Explanations

terms related to self-service and automated systems

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

Automated or self-service processes

np_acts-logits-general · gemini-2.0-flash

self-operated or automated processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

writeFieldEnd

-0.65

MigrationBuilder

-0.48

postsleuth

-0.45

windowFixed

-0.42

 jScrollPane

-0.42

Personensuche

-0.39

səhifə

-0.38

TableField

-0.38

vician

-0.37

ibilidad

-0.37

POSITIVE LOGITS

 automat

0.56

 impersonal

0.56

 automated

0.56

 automatic

0.53

automated

0.52

自動

0.52

staticmethod

0.51

automatic

0.50

Automated

0.50

 automate

0.50

Activations Density 0.565%

terms related to self-service and automated systems

Automated or self-service processes

self-operated or automated processes

No Comments

No Known Activations