INDEX

Explanations

references to projects or initiatives

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

named projects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

قایناق‌لار

-0.60

toMatchSnapshot

-0.54

MethodManager

-0.54

exitRule

-0.50

tenham

-0.47

 CreateTagHelper

-0.46

 springfox

-0.46

haden

-0.45

leans

-0.45

bark

-0.45

POSITIVE LOGITS

 project

1.26

 Project

1.07

project

1.06

Project

0.98

 proyecto

0.97

 PROJECT

0.97

 Projekt

0.95

 projekt

0.90

 projeto

0.86

 projet

0.86

Activations Density 0.028%

references to projects or initiatives

named projects

No Comments

No Known Activations