INDEX

Explanations

terms related to duration or length, especially in a scientific or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Picchu

-0.66

неопр

-0.64

 później

-0.59

ngdoc

-0.58

indest

-0.56

 אלה

-0.56

 Alcott

-0.55

 însă

-0.55

وردار

-0.55

ództ

-0.54

POSITIVE LOGITS

1.01

 onAnimation

0.79

DeleteBehavior

0.65

‑

0.63

}$-

0.59

 FontWeight

0.59

ंदीखरीदारी

0.58

‐

0.57

 ddelweddau

0.56

-/

0.56

Activations Density 0.961%

terms related to duration or length, especially in a scientific or technical context

No Comments

No Known Activations