INDEX

Explanations

phrases related to focus and concentration on specific subjects or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tarvit

-0.59

 paik

-0.57

 witnessed

-0.56

cemia

-0.53

ersk

-0.51

ni

-0.50

 disposent

-0.50

rdı

-0.50

nick

-0.49

をご

-0.49

POSITIVE LOGITS

Autoritní

0.76

 AssemblyCulture

0.76

richTextPanel

0.75

+#+#

0.69

SourceChecksum

0.69

WebElementEntity

0.65

 autorytatywna

0.64

 matters

0.64

 perfecting

0.63

Hauptartikel

0.62

Activations Density 0.217%

phrases related to focus and concentration on specific subjects or topics

No Comments

No Known Activations