INDEX

Explanations

terms related to destruction or damaging actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

zeitige

-0.71

 aient

-0.64

 fraî

-0.64

 Fingers

-0.63

 devront

-0.61

قایناق‌لار

-0.60

 doulou

-0.59

 pince

-0.59

 firent

-0.58

лерея

-0.58

POSITIVE LOGITS

estroying

1.38

 Destroy

1.32

Destroy

1.32

DESTROY

1.31

 destroy

1.27

 destruction

1.27

 Destruction

1.25

 destru

1.23

 destroyed

1.20

 Destroyer

1.19

Activations Density 0.185%

terms related to destruction or damaging actions

No Comments

No Known Activations