INDEX

Explanations

references to meta concepts and self-awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

@[+][

-0.69

djangoproject

-0.69

脚注の使い方

-0.67

dotenv

-0.63

sizeCache

-0.62

 resourceCulture

-0.62

barui

-0.62

dflare

-0.60

PageRoute

-0.59

 initComponents

-0.59

POSITIVE LOGITS

 introspection

0.53

 itself

0.52

 faculty

0.51

 analyse

0.50

 mécan

0.50

 consci

0.49

 realise

0.48

 analysing

0.47

itself

0.46

Abp

0.46

Activations Density 0.393%

references to meta concepts and self-awareness

No Comments

No Known Activations