INDEX

Explanations

terms related to motion or moving actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

:✨

-0.65

 getItemId

-0.62



-0.59

 fossero

-0.58

DispatchToProps

-0.58

 disambiguazione

-0.58

 bulge

-0.57

 unmute

-0.57

 avesse

-0.56

цездатний

-0.55

POSITIVE LOGITS

 moving

3.19

 Moving

2.88

moving

2.79

Moving

2.78

 MOVING

2.52

 rotating

1.18

 going

1.15

 relocating

1.10

rotating

1.07

 shifting

1.06

Activations Density 0.115%

terms related to motion or moving actions

No Comments

No Known Activations