INDEX

Explanations

questions and inquiry phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ioutil

-0.57

caj

-0.57

brainly

-0.56

anneer

-0.55

 UIView

-0.55

Essen

-0.55

בות

-0.54

 المعيارى

-0.54

Enlaces

-0.54

ami

-0.54

POSITIVE LOGITS

 dumne

0.66

 quelcon

0.65

 civiles

0.65

CGRectMake

0.60

 kasarigan

0.59

 îna

0.59

 combien

0.57

hyrchwyd

0.56

 ljudi

0.56

 laikā

0.56

Activations Density 0.078%

questions and inquiry phrases

No Comments

No Known Activations

questions and inquiry phrases

No Comments

No Known Activations