INDEX

Explanations

terms and phrases related to regulations and legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 quidem

-0.37

tissement

-0.33

Fa

-0.33

HasValue

-0.33

Penulis

-0.32

fa

-0.32

 Besøkt

-0.32

deckte

-0.32

Fa

-0.31

źródło

-0.31

POSITIVE LOGITS

DockStyle

0.69

󠁢

0.68

 للمعارف

0.61

 صوتيه

0.60

skjaer

0.59

󠁮

0.55

BufferException

0.55

ftagPool

0.54

="@+

0.54

MLLoader

0.53

Activations Density 0.670%

terms and phrases related to regulations and legal contexts

No Comments

No Known Activations