INDEX

Explanations

present and past continuous actions occurring in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 <<<<<<<<<<<<<<

-0.82

Datuak

-0.78

 vectorielle

-0.75

lieferung

-0.74

 juridiques

-0.73

 térm

-0.69

 AppColors

-0.69

 cielos

-0.68

mybatisplus

-0.67

 anisotropic

-0.66

POSITIVE LOGITS

 doing

1.58

 Doing

1.52

Doing

1.50

 DOING

1.43

doing

1.38

 doin

1.33

 doings

1.01

Do

1.01

Do

0.96

 done

0.94

Activations Density 0.034%

present and past continuous actions occurring in the text

No Comments

No Known Activations