INDEX

Explanations

statements of purpose or intention

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

statements of intent or purpose introduced by words like "aim," "goal," or "intent."

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/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.31.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

 hyö

-0.41

 kysy

-0.40

 Umständen

-0.39

 voidaan

-0.36

 виправивши

-0.35

 couronne

-0.34

jalna

-0.33

 protagonistas

-0.32

 Altos

-0.32

 fourrure

-0.32

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.75

 isto

0.67

extAlignment

0.61

UnusedPrivate

0.59

migrationBuilder

0.56

parsedMessage

0.56

WebVitals

0.55

 BorderRadius

0.54

FDRE

0.54

crollView

0.53

Activations Density 0.244%

statements of purpose or intention

statements of intent or purpose introduced by words like "aim," "goal," or "intent."

No Comments

No Known Activations