INDEX

Explanations

programming imports related to libraries and modules

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

Beginning of turn marker

np_acts-logits-general · gemini-2.0-flash

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 мәкал

-0.58

 تكبرها

-0.54

UnusedPrivate

-0.51

AISSEE

-0.47

StandardCharsets

-0.47

SOUNDBITE

-0.46

 kaarangay

-0.46

 виправивши

-0.46

 дописавши

-0.46

Чыганаклар

-0.46

POSITIVE LOGITS

 الحره

0.51

Wrap

0.42

Dat

0.40

Rom

0.40

 Wrap

0.39

Roll

0.39

 initComponents

0.39

исленность

0.38

 Stroll

0.38

XmlAccessType

0.38

Activations Density 0.070%

programming imports related to libraries and modules

Beginning of turn marker

<start_of_turn>user

No Comments

No Known Activations