INDEX

Explanations

system commands and functions related to output control in programming

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

rungsseite

-0.55

 EconPapers

-0.51

 createSlice

-0.48

⟬

-0.48

chtest

-0.47

 indisponible

-0.47

対

-0.46



-0.46

mazoo

-0.46

 InputDecoration

-0.45

POSITIVE LOGITS

 command

0.46

Command

0.42

 Command

0.42

system

0.42

clear

0.41

清

0.41

DllImport

0.41

 nahilalakip

0.40

таратура

0.40

QMetaType

0.39

Activations Density 0.003%

system commands and functions related to output control in programming

<start_of_turn> user

No Comments

No Known Activations