INDEX

Explanations

phrases indicating awareness or common knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 estekak

-0.74

Personensuche

-0.72

ThroughAttribute

-0.70

 tartalomajánló

-0.70

SharedCtor

-0.69

TestingModule

-0.68

LookAnd

-0.67

Euer

-0.67

Hochspringen

-0.67

::~

-0.66

POSITIVE LOGITS

 famous

0.54

 recent

0.53

 notorious

0.51

ご存知

0.50

 recently

0.48

 familiar

0.48

0.47

 извест

0.46

 famously

0.46

 infamous

0.44

Activations Density 0.173%

phrases indicating awareness or common knowledge

No Comments

No Known Activations