INDEX

Explanations

phrases related to design and quality in products or services

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

a more cost

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 gydy

-0.40

acijos

-0.38

ísimo

-0.38

aringan

-0.34

 Selain

-0.34

inį

-0.33

 Komunikasi

-0.32

 pysty

-0.32

 vandens

-0.32

 mémoire

-0.32

POSITIVE LOGITS

RectangleBorder

0.70

GraphicsUnit

0.63

iprot

0.59

$_"

0.59

 hObject

0.57

SequentialGroup

0.56

localctx

0.55

󠁿

0.55

WithMany

0.55

 ſelbſt

0.55

Activations Density 0.009%

phrases related to design and quality in products or services

a more cost

No Comments

No Known Activations