INDEX

Explanations

negative connotations related to the decline of value or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-_-

-0.68

 anticor

-0.66

 seiz

-0.65

 interse

-0.64



-0.63

$(-

-0.63

 dissol

-0.63

InputBorder

-0.62

DIP

-0.62

 curs

-0.62

POSITIVE LOGITS

–

1.05

0.77

—

0.74

--

0.66

 Gegenteil

0.58

->

0.56

 Grüsse

0.56

 aikaa

0.55

 Ausnahme

0.53

 Realität

0.53

Activations Density 0.646%

negative connotations related to the decline of value or quality

No Comments

No Known Activations