INDEX

Explanations

terms related to medical imaging and tumour characteristics

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

ending in "isation" or similar suffixes

np_acts-logits-general · gemini-2.0-flash

-isation suffix

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

 Ее

-1.66

 theater

-1.53

Еще

-1.52

 Еще

-1.51

ьез

-1.46

 neighbors

-1.45

ighbor

-1.41

ighborhood

-1.40

 theaters

-1.39

 favorite

-1.39

POSITIVE LOGITS

Ещё

2.45

 fertiliser

2.33

 civilisation

2.31

 realisation

2.31

 generalised

2.30

 optimisation

2.30

 organisation

2.30

 organisational

2.30

şi

2.29

 utilisation

2.28

Activations Density 3.206%

terms related to medical imaging and tumour characteristics

ending in "isation" or similar suffixes

-isation suffix

No Comments

No Known Activations