INDEX

Explanations

mentions of geographic locations or regional identifiers

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

movement or change of state

np_acts-logits-general · gemini-2.0-flash

actions and changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 chemical

-0.31

 appunto

-0.30

 professional

-0.29

layui

-0.29

 chemicals

-0.27

Distribuzione

-0.27

 useContext

-0.27

 arit

-0.26

 organizations

-0.26

 lingü

-0.26

POSITIVE LOGITS

WithIOException

0.64

 kasarigan

0.62

 архивлан

0.61

 FacebookSign

0.61

ſſung

0.60

igraph

0.58

нгред

0.58

ſicht

0.57

ReusableCell

0.57

nages

0.56

Activations Density 1.442%

mentions of geographic locations or regional identifiers

movement or change of state

actions and changes

No Comments

No Known Activations