INDEX

Explanations

terms related to health conditions or medical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Vidite

-0.80

mergeFrom

-0.76

 externi

-0.72

 صوتيه

-0.72

تفصیلات

-0.71

клопе

-0.69

 snippetHide

-0.67

writeField

-0.66

 Infórmanos

-0.65

олові

-0.65

POSITIVE LOGITS

+"/"+

0.49

(:,:,

0.47

tal

0.44

Plug

0.44

Powered

0.44

discuss

0.43

Wired

0.42

|/

0.42

)}</

0.42

ObjectModel

0.41

Activations Density 0.696%

terms related to health conditions or medical terminology

No Comments

No Known Activations