INDEX

Explanations

phrases indicating probabilities and chances

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.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

__(/*!

-0.51

 GenerationType

-0.49

 joindre

-0.48

 FetchType

-0.45

 Bedürfnisse

-0.43

ardes

-0.42

Atoi

-0.39

 članak

-0.38

conio

-0.38

 encantan

-0.38

POSITIVE LOGITS

 chances

2.79

 chance

2.60

 probability

2.54

 likelihood

2.40

 Chances

2.33

 odds

2.31

Chances

2.25

chance

2.17

probability

2.14

 probabilities

2.12

Activations Density 0.424%

phrases indicating probabilities and chances

No Comments

No Known Activations