INDEX

Explanations

contexts involving confrontations with law enforcement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

grande

-0.49

nina

-0.47

нибудь

-0.47

hedrals

-0.45

 morrow

-0.44

ordinary

-0.44

 annum

-0.43

promote

-0.43

 modern

-0.43

odes

-0.43

POSITIVE LOGITS

 doInBackground

0.72

帖最后由

0.66

########.

0.65

ProcessEvent

0.63

 sempat

0.63

 ICommand

0.62

bootstrapcdn

0.62

 getItemId

0.62

---*/

0.60

regon

0.60

Activations Density 0.418%

contexts involving confrontations with law enforcement

No Comments

No Known Activations