INDEX

Explanations

instances of the word "behaviour" and its variations

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

containing "our", especially "behaviour"

np_acts-logits-general · gemini-2.0-flash

behaviour, labour, honor, tumor, favours

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Ewig

-0.41

Clik

-0.40

vensk

-0.39

 Frankrijk

-0.39

 Seti

-0.38

ipedia

-0.38

 importance

-0.38

 Newt

-0.37

XT

-0.36

POSITIVE LOGITS

bour

0.64

 Neighbor

0.59

 Neighbourhood

0.59

onBlur

0.59

lour

0.59

bourhood

0.58

honor

0.57

 NEIGH

0.56

NoSuchAlgorithm

0.56

Neighbor

0.55

Activations Density 0.356%

instances of the word "behaviour" and its variations

containing "our", especially "behaviour"

behaviour, labour, honor, tumor, favours

No Comments

No Known Activations