INDEX

Explanations

references to names or terms associated with "kn" and "knu," indicating a focus on specific individuals, titles, or concepts

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

starting with "Kn" or "kn"

np_acts-logits-general · gemini-2.0-flash

words starting Kn

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

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

 resourceCulture

-0.53

存于互联网档案馆

-0.46

PYX

-0.46

AccessorTable

-0.44

 насељу

-0.43

 Yolanda

-0.43

 UIColor

-0.43

पया

-0.42

stalt

-0.42

Explicación

-0.41

POSITIVE LOGITS

Kn

0.81

Kn

0.77

kn

0.73

Kni

0.68

KN

0.65

Kno

0.63

Kni

0.59

kn

0.57

Kno

0.56

Kna

0.55

Activations Density 0.104%

references to names or terms associated with "kn" and "knu," indicating a focus on specific individuals, titles, or concepts

starting with "Kn" or "kn"

words starting Kn

No Comments

No Known Activations