INDEX

Explanations

variations of the word "sharp" in different contexts

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

"sharp"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MathML

-0.45

</table>

-0.44

StoryboardSegue

-0.38

 radiador

-0.38

\{\\

-0.37

wegen

-0.37

Libro

-0.37

Pä

-0.37

ésult

-0.37

Plate

-0.37

POSITIVE LOGITS

 Sharp

1.21

 sharp

1.16

sharp

1.15

Sharp

1.09

 SHARP

1.03

 sharpness

1.01

 sharper

0.97

 sharpen

0.95

 tajam

0.91

 sharpened

0.85

Activations Density 0.091%

variations of the word "sharp" in different contexts

"sharp"

No Comments

No Known Activations