INDEX

Explanations

names of medical institutions and related healthcare professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Referencies

-0.49

kloped

-0.44

msford

-0.44

béco

-0.42

doctype

-0.42

flo

-0.42

@"/

-0.41

 circulaire

-0.41

IActionResult

-0.41

 enca

-0.40

POSITIVE LOGITS

 समीक्षक

0.69

addCriterion

0.67

KURZBESCHREIBUNG

0.65

cotch

0.65

 незавершена

0.63

ViewInit

0.58

delwed

0.58

 handleMessage

0.58

 Government

0.56

 Asian

0.55

Activations Density 0.136%

names of medical institutions and related healthcare professionals

No Comments

No Known Activations