INDEX

Explanations

terms related to motion and moving images

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

 surla

-0.82

ífico

-0.76

adecimal

-0.75

 Paglinawan

-0.74

PerformLayout

-0.74

 cervello

-0.74

 soát

-0.73

gridx

-0.73

czaj

-0.73

crocs

-0.72

POSITIVE LOGITS

 motion

3.59

 Motion

3.31

motion

3.20

Motion

3.17

 MOTION

3.09

 motions

2.86

 Motions

2.66

MOTION

2.56

motions

2.31

 movement

1.78

Activations Density 0.076%

terms related to motion and moving images

No Comments

No Known Activations