INDEX

Explanations

indicators of additional content or calls to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

__*/

-0.97

الحياه

-0.77

بوابة

-0.77

 समीक्षाएं

-0.73

 indisponible

-0.73

PhysRev

-0.66

PhysRevD

-0.66

 '\\;'

-0.65

 kaarangay

-0.65

Kariera

-0.64

POSITIVE LOGITS

<eos>

1.12

Попис

0.53

 judiciales

0.51

 Económica

0.51

).)

0.49

<unused60>

0.46

 Idem

0.45

 gunner

0.45

 récente

0.44

jir

0.43

Activations Density 0.172%

indicators of additional content or calls to action

No Comments

No Known Activations