INDEX

Explanations

references to legal processes and court-related terminology

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

following "of", "the", "be"

np_acts-logits-general · gemini-2.0-flash

performing actions or occurrences

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

verifyException

-0.43

ssymb

-0.40

evos

-0.40

Rename

-0.39

Instal

-0.39

 divis

-0.39

 transl

-0.39

AnimationsModule

-0.38

Revel

-0.38

findall

-0.38

POSITIVE LOGITS

 hacerlo

0.54

การ

0.53

 történ

0.53

 farlo

0.51

 ModelExpression

0.50

 efectuar

0.50

 việc

0.49

 melakukannya

0.48

 erfolgt

0.47

进行

0.46

Activations Density 1.457%

references to legal processes and court-related terminology

following "of", "the", "be"

performing actions or occurrences

No Comments

No Known Activations