INDEX

Explanations

the term "notable" and its variants, indicating significant or worthy mentions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

basicConfig

-0.71

 yaşad

-0.59

icoot

-0.57

Extinguishing

-0.56

 exhausted

-0.55

Perfection

-0.53

 autorytatywna

-0.52

хьтан

-0.51

URLException

-0.51

 answers

-0.51

POSITIVE LOGITS

 notable

3.27

 Notable

2.89

Notable

2.53

 noteworthy

2.42

 notably

2.35

 noticeable

2.26

 notables

1.94

 Notably

1.75

 noticeably

1.72

 conspicuous

1.57

Activations Density 0.104%

the term "notable" and its variants, indicating significant or worthy mentions in various contexts

No Comments

No Known Activations