INDEX

Explanations

terms related to comparison and complexity

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

starting with "Comp" or "comp"

np_acts-logits-general · gemini-2.0-flash

comp- words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

cipital

-0.68



-0.60

Mutagenicity

-0.57

teh

-0.55

حياته

-0.54

DeleteBehavior

-0.54

 للمعارف

-0.53

الحياه

-0.53

(!__

-0.51

POSITIVE LOGITS

COMPR

0.75

 COMP

0.73

COMP

0.69

 Comp

0.69

 Compton

0.66

COM

0.65

comp

0.65

Comp

0.65

 compr

0.61

COM

0.60

Activations Density 0.197%

terms related to comparison and complexity

starting with "Comp" or "comp"

comp- words

No Comments

No Known Activations