INDEX

Explanations

phrases related to authority and control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

ſelf

-0.75

SpringBootTest

-0.63

 ſtate

-0.60

 ſta

-0.59

(__('

-0.58

 ſche

-0.57

{*}

-0.57

 pleaſure

-0.57

 faſt

-0.56

 ujednoznacz

-0.55

POSITIVE LOGITS

 meille

0.45

 ilman

0.43

 vermelhas

0.43

 Tiefen

0.42

 Encuentra

0.42

 väh

0.42

 것은

0.39

 เต

0.39

 eikä

0.39

 daž

0.39

Activations Density 0.041%

phrases related to authority and control

No Comments

No Known Activations