INDEX

Explanations

phrases related to time-sensitive actions and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

queryInterface

-0.48

 Paramètres

-0.46

 wezen

-0.42

 MEJOR

-0.42

 belangrij

-0.42

 rodzaju

-0.42

 carottes

-0.41

 zoude

-0.40

 gereja

-0.40

 lepiej

-0.40

POSITIVE LOGITS

few

0.65

Two

0.60

 Three

0.59

Few

0.59

 couple

0.58

 Four

0.58

Six

0.58

 above

0.56

 around

0.55

 Five

0.54

Activations Density 0.327%

phrases related to time-sensitive actions and conditions

No Comments

No Known Activations