INDEX

Explanations

phrases or terms related to numerical values or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

WebVitals

-0.79

出版年

-0.66

bardier

-0.62

ValueStyle

-0.61

EndInit

-0.59

 समीक्षाओं

-0.57

󠁴

-0.53

MessageTagHelper

-0.51

Hentet

-0.50

ścic

-0.50

POSITIVE LOGITS

 nakalista

0.59

 maximal

0.56

ArgsConstructor

0.56

__":

0.54

抵

0.53

 podjela

0.52

])).

0.52

 joaat

0.52

 maximum

0.50

')):

0.50

Activations Density 1.047%

phrases or terms related to numerical values or identifiers

No Comments

No Known Activations