INDEX

Explanations

terms and concepts related to configuration and settings in programming or software applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

expandindo

-0.82

SourceChecksum

-0.79

WebServlet

-0.77

 BIBSYS

-0.74

ChildScrollView

-0.72

MockMvc

-0.69

 autorytatywna

-0.68

 ControllerBase

-0.66

GEBURTSDATUM

-0.66

IActionResult

-0.66

POSITIVE LOGITS

 settings

1.15

settings

1.07

 configuration

1.07

 Settings

1.04

Settings

1.03

 config

1.03

config

1.02

 configurations

0.98

Config

0.97

cfg

0.97

Activations Density 0.353%

terms and concepts related to configuration and settings in programming or software applications

No Comments

No Known Activations