INDEX

Explanations

technical terms and parameters related to image processing and network protocols

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

network protocol names, chemical formulas, or code snippets

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

SharedCtor

-0.54

 utafitiHapana

-0.49

TagMode

-0.49

 Biôgrafia

-0.48

 kaarangay

-0.47

 SwitchCompat

-0.46

EndProject

-0.45

enumii

-0.44

 Photocase

-0.44

PushMatrix

-0.44

POSITIVE LOGITS

PyObject

0.81

 PyObject

0.78

ommen

0.50

pexpr

0.47

pym

0.45

eer

0.44

 Cleo

0.44

thme

0.42

 sphinx

0.41

PHA

0.41

Activations Density 0.001%

technical terms and parameters related to image processing and network protocols

network protocol names, chemical formulas, or code snippets

No Comments

No Known Activations