INDEX

Explanations

parts of speech that indicate brand names, affiliations, and conjunctions in sentences

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

Comes before a name

np_acts-logits-general · gemini-2.0-flash

detected the

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 EconPapers

-0.81

 للمعارف

-0.77

IVEREF

-0.69

 utafitiHapana

-0.65

ConstraintMaker

-0.63

nestjs

-0.63

\{\\

-0.60

ArgsConstructor

-0.59

 αυτή

-0.59

出版年

-0.58

POSITIVE LOGITS

vetica

0.58

":[{

0.49

glGen

0.48

__":

0.48

 invokingState

0.48

CopyWith

0.47

ULAS

0.47

<",

0.45

Distribuzione

0.45

ALE

0.43

Activations Density 1.552%

parts of speech that indicate brand names, affiliations, and conjunctions in sentences

Comes before a name

detected the

No Comments

No Known Activations