INDEX

Explanations

interrogative phrases and expressions of concern regarding societal issues

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himself

-0.50

 addresses

-0.43

 consiglio

-0.40

 görül

-0.39

ipel

-0.39

himself

-0.37

تين

-0.37

弁

-0.36

 yaptı

-0.36

linearGradient

-0.35

POSITIVE LOGITS

ISupport

0.75

 unga

0.69

\{\\

0.66

Попис

0.65

__*/

0.64

toMatchSnapshot

0.64

 excru

0.64

 ActivatedRoute

0.64

 ActionResult

0.63

adaptiveStyles

0.63

Activations Density 0.123%

interrogative phrases and expressions of concern regarding societal issues

No Comments

No Known Activations