INDEX

Explanations

terms related to capacity and occupancy in various contexts

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

associated with being full or crowded

np_acts-logits-general · gemini-2.0-flash

filled, packed, crowded

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Kanpo

-0.61

SourceChecksum

-0.58

 oprot

-0.55

ftagPool

-0.55

Kaynakça

-0.55

enumi

-0.52

UNRELATED

-0.50

angal

-0.50

UIControlState

-0.50

idios

-0.49

POSITIVE LOGITS

 filled

1.63

 filling

1.55

 fill

1.50

 fills

1.45

 Filled

1.42

Filling

1.34

 Filling

1.33

 full

1.30

filled

1.30

 packed

1.30

Activations Density 0.233%

terms related to capacity and occupancy in various contexts

associated with being full or crowded

filled, packed, crowded

No Comments

No Known Activations