INDEX

Explanations

concepts related to health and well-being, especially in medical contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•Helix list

No Comments

Negative Logits

 "..\..\..\

-0.58

 незавершена

-0.57

 "..\..\

-0.57

Dr

-0.50

“

-0.46

PerformLayout

-0.45

 nửa

-0.43

Dr

-0.43

inquirer

-0.43

its

-0.42

POSITIVE LOGITS

ंदीखरीदारी

0.83

 witches

0.78

 lamella

0.76

 holotype

0.72

 forester

0.72

Filmografie

0.71

 labourers

0.70

 дописавши

0.68

 negroes

0.68

 blacksmith

0.68

Activations Density 0.379%

concepts related to health and well-being, especially in medical contexts

No Comments

No Known Activations