INDEX

Explanations

terms related to physical activity intensity levels

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

arius

-0.60

 EClass

-0.59

-0.56

шеб

-0.56

hus

-0.56

Gdx

-0.55

 ddelweddau

-0.55

IsInitialized

-0.55

腑

-0.54

sk

-0.54

POSITIVE LOGITS

 moderate

2.57

 Moderate

2.48

Moderate

2.48

moderate

2.35

 moderation

2.17

 moderated

2.14

 MODER

2.08

 moder

2.07

 Moder

1.98

Moder

1.91

Activations Density 0.098%

terms related to physical activity intensity levels

No Comments

No Known Activations