INDEX

Explanations

references to legal issues and procedural terminology

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

 تكبرها

-0.59

BufferException

-0.51

runOnUiThread

-0.50

 algemeen

-0.49

šanās

-0.48

dessous

-0.47

 oeufs

-0.47

äsche

-0.46

例文

-0.46

 persoane

-0.46

POSITIVE LOGITS

 betweenstory

0.81

 utafitiHapana

0.79

 समीक्षक

0.74

 '\\;'

0.73

 unleashed

0.68

 unforgettable

0.65

 awaits

0.62

($__

0.60

anskje

0.60

Activations Density 0.966%

references to legal issues and procedural terminology

No Comments

No Known Activations