INDEX

Explanations

technical terms and function definitions related to programming and data processing

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

ending in "Function", "launch", or "NAME"

np_acts-logits-general · gemini-2.0-flash

launch.desktop, function(), independence(), name_state, insta]

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.63

 parha

-0.52

rinfo

-0.52

 servici

-0.51

 främ

-0.51

 centru

-0.50

KEYCODE

-0.50

tableFuture

-0.49

IFEST

-0.49

หลัก

-0.49

POSITIVE LOGITS

 שוליים

0.89

OGND

0.68

 intptr

0.62

存于互联网档案馆

0.62

 Plus

0.60

 Without

0.60

带

0.59

 without

0.58

енча

0.57

with

0.57

Activations Density 0.763%

technical terms and function definitions related to programming and data processing

ending in "Function", "launch", or "NAME"

launch.desktop, function(), independence(), name_state, insta]

No Comments

No Known Activations