INDEX

Explanations

structured data responses in a programming context

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

Strings associated with web responses

np_acts-logits-general · gemini-2.0-flash

success messages or responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Pap

-0.39

residual

-0.34

butterfly

-0.33

見学

-0.32

 Neglect

-0.32

 refer

-0.32

興味

-0.32

-0.31

 PRES

-0.31

 probably

-0.31

POSITIVE LOGITS

LookAnd

0.77

esModule

0.71

IntoConstraints

0.68

featureID

0.68

Tembelea

0.65

IVEREF

0.64

MigrationBuilder

0.62

ésultats

0.62

ChildScrollView

0.61

 avoient

0.60

Activations Density 0.106%

structured data responses in a programming context

Strings associated with web responses

success messages or responses

No Comments

No Known Activations