INDEX

Explanations

references to "Arch" and its various contextual usages

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

"Arch" or "arch"

np_acts-logits-general · gemini-2.0-flash

arch, architecture, arch pairs

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

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

stdc

-0.37

ren

-0.37

Joe

-0.35

joba

-0.35

-0.34

 rever

-0.33

Terry

-0.33

PLA

-0.33

Rptr

-0.33

zuf

-0.33

POSITIVE LOGITS

 Arch

0.76

 arch

0.74

 ARCH

0.71

 Archi

0.65

Arch

0.62

 archi

0.60

 Arco

0.60

 Arches

0.59

 arquitetura

0.59

 Архи

0.58

Activations Density 0.127%

references to "Arch" and its various contextual usages

"Arch" or "arch"

arch, architecture, arch pairs

No Comments

No Known Activations