INDEX

Explanations

words and phrases associated with tools, methods, and leadership in various contexts

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

instruments or resources

np_acts-logits-general · gemini-2.0-flash

tools and means

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

bited

-0.74

CodedInputStream

-0.71

はじめに

-0.65

 Италијани

-0.64

webElementXpaths

-0.62

 sponsorship

-0.60

]--;

-0.60

 disambiguazione

-0.60

 Anmeldung

-0.58

 sponsoring

-0.57

POSITIVE LOGITS

 tools

1.20

 arsenal

1.10

 toolbox

1.07

tools

1.02

 tool

1.00

 toolkit

0.96

 Tools

0.96

 outils

0.93

Tools

0.92

 herramientas

0.89

Activations Density 0.410%

words and phrases associated with tools, methods, and leadership in various contexts

instruments or resources

tools and means

No Comments

No Known Activations