INDEX

Explanations

references to the letter 'K'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

httphttps

-0.71

 autorytatywna

-0.63

GEBURTS

-0.62

WriteBarrier

-0.59

 nahilalakip

-0.54

рем

-0.52

FormTagHelper

-0.52

جوايز

-0.51

 full

-0.50

zerű

-0.48

POSITIVE LOGITS

 SMEs

0.42

 Cinemat

0.42

pă

0.41

 proximate

0.40

unknownFields

0.40

 pâtes

0.40

 moins

0.39

ChromeDriver

0.39

 surnames

0.39

 Allociné

0.38

Activations Density 0.240%

references to the letter 'K'

No Comments

No Known Activations