INDEX

Explanations

variations of the verb "have."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 noemen

-0.80

prefixer

-0.78

tagHelper

-0.77

Климат

-0.77

 resourceCulture

-0.76

 vectorielle

-0.67

máscara

-0.66

 zorgen

-0.66

 tambi

-0.65

are

-0.64

POSITIVE LOGITS

had

0.98

Had

0.87

 have

0.83

have

0.83

Had

0.81

had

0.77

 having

0.76

Having

0.74

 Having

0.70

Have

0.70

Activations Density 0.090%

variations of the verb "have."

No Comments

No Known Activations