INDEX

Explanations

terms related to legal and procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Źródło

-0.57

帖最后由

-0.55

̈́

-0.54

wszy

-0.54

Hentet

-0.54

newswire

-0.54

 Tuttle

-0.53

ellum

-0.52

 مرئيه

-0.52

Nieuw

-0.51

POSITIVE LOGITS

 Normdatei

0.90

 Paglinawan

0.61

__*/

0.51

%"),

0.51

 nød

0.49

oa̍t

0.49

новништво

0.48

 onData

0.45

]+=

0.45

:✨

0.44

Activations Density 0.800%

terms related to legal and procedural contexts

No Comments

No Known Activations