INDEX

Explanations

terms related to processing and handling information or data, particularly in technical contexts

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

Scientific or technical processes

np_acts-logits-general · gemini-2.0-flash

technical processes and their metrics

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

ImageField

-0.78

contentLoaded

-0.68

viamo

-0.60

 Gruber

-0.60

accharides

-0.59

 Schuster

-0.58

gehalt

-0.58

wayne

-0.57

Wex

-0.57

angliski

-0.57

POSITIVE LOGITS

 process

0.58

 assisti

0.57

AndUpdate

0.57

 AsyncTask

0.56

 effettu

0.56

process

0.53

をする

0.52

twimg

0.51

able

0.50

hyrchwyd

0.50

Activations Density 1.192%

terms related to processing and handling information or data, particularly in technical contexts

Scientific or technical processes

technical processes and their metrics

No Comments

No Known Activations