INDEX

Explanations

statistical measurements and comparisons in data

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

Statistical means or averages

np_acts-logits-general · gemini-2.0-flash

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

رشف

-0.57

 كومونز

-0.47

endphp

-0.43

llary

-0.42

 للمعارف

-0.41

хьтан

-0.41

 onCreateView

-0.40

kuuta

-0.40

Chham

-0.39

transQ

-0.38

POSITIVE LOGITS

 average

2.86

average

2.48

Average

2.44

 Average

2.44

平均

2.28

 averages

2.27

 AVERAGE

2.23

 averaged

2.16

AVERAGE

2.09

avg

2.08

Activations Density 1.294%

statistical measurements and comparisons in data

Statistical means or averages

No Comments

No Known Activations