INDEX

Explanations

names and terms associated with medical and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.78

Rao

-0.68

ness

-0.65

 Gaines

-0.64

 Martinez

-0.64

 Schle

-0.63

 beans

-0.62

RICAL

-0.62

дз

-0.61

])[

-0.60

POSITIVE LOGITS

клопе

0.94

DMR

0.92

 вікі

0.89

 considérons

0.87

troppo

0.86

sī

0.83

Gua

0.80

CppMethod

0.80

 viscose

0.80

 Всё

0.80

Activations Density 1.498%

names and terms associated with medical and technical contexts

No Comments

No Known Activations