INDEX

Explanations

references to media appearances and collaborations in the context of professional achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 createSprite

-0.64

tagHelper

-0.53

Viitteet

-0.53

 Audiodateien

-0.52

ביוגרפיה

-0.51

//}

-0.51

-0.50

 dubbel

-0.49

קישורים

-0.49

GOTREF

-0.48

POSITIVE LOGITS

 across

0.64

 ACROSS

0.61

 GenerationType

0.56

 ranging

0.56

addGap

0.56

 partout

0.54

 dozens

0.52

StoryboardSegue

0.51

 Paglinawan

0.51

 range

0.51

Activations Density 0.276%

references to media appearances and collaborations in the context of professional achievements

No Comments

No Known Activations