INDEX

Explanations

references to specific locations and technical vocabulary related to programming

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

after "Buffalo"

np_acts-logits-general · gemini-2.0-flash

Buffalo River or vim configuration

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

tagext

-0.56

Ell

-0.52

 reactiv

-0.52

 Crom

-0.52

tenham

-0.52

DMETHOD

-0.52

 Bain

-0.51

Ell

-0.49

distrito

-0.49

 rhestr

-0.49

POSITIVE LOGITS

 propOrder

0.44

 arşivlendi

0.40

 forState

0.37

 Corolla

0.34

Toyota

0.33

 crossorigin

0.32

Buffalo

0.32

 corolla

0.31

 ویکی‌پدیا

0.31

 Toyota

0.31

Activations Density 0.377%

references to specific locations and technical vocabulary related to programming

after "Buffalo"

Buffalo River or vim configuration

No Comments

No Known Activations