INDEX

Explanations

occurrences of the word "despite" and its variations, indicating contrasts or counterarguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

mozilla

-0.60

 Hamm

-0.58

kem

-0.57

ึ้น

-0.57

way

-0.55

Child

-0.54

 savoir

-0.54

 tunn

-0.54

 Child

-0.54

 Jame

-0.53

POSITIVE LOGITS

ostante

1.79

 despite

1.66

despite

1.63

 Despite

1.54

Despite

1.48

 nonostante

1.44

 spite

1.31

 Malgré

1.29

 Trotz

1.29

 apesar

1.24

Activations Density 0.088%

occurrences of the word "despite" and its variations, indicating contrasts or counterarguments

No Comments

No Known Activations