INDEX

Explanations

references to user actions and system requirements

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

preceding auxiliary verbs

np_acts-logits-general · gemini-2.0-flash

need to / have to

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

ureux

-0.51

MigrationBuilder

-0.51

Ārējās

-0.49

gestone

-0.48

createCanvas

-0.46

SUCCEEDED

-0.46

DispatchToProps

-0.45

 JpaRepository

-0.45

SharedDtor

-0.44

avax

-0.44

POSITIVE LOGITS

 need

2.44

need

2.19

 Need

2.10

Need

2.06

 needing

1.94

 needs

1.88

 necessity

1.85

 NEED

1.78

 require

1.78

 requires

1.77

Activations Density 0.949%

references to user actions and system requirements

preceding auxiliary verbs

need to / have to

No Comments

No Known Activations