INDEX

Explanations

technical terms and syntactical constructs related to programming or mathematical logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

RenderAtEndOf

-0.90

GEBURTSDATUM

-0.66

󠁴

-0.60

StoryboardSegue

-0.57

Tikang

-0.54

 ujednoznacz

-0.53

elemField

-0.52

⤹

-0.51

ConverterFactory

-0.50

 الحره

-0.50

POSITIVE LOGITS

новниш

0.40

andExpect

0.39

 giras

0.38

 Paglinawan

0.38

 scolaire

0.36

Props

0.36

 Respon

0.36

 así

0.36

 authentique

0.36

Референце

0.36

Activations Density 0.509%

technical terms and syntactical constructs related to programming or mathematical logic

No Comments

No Known Activations