INDEX

Explanations

references to "angiotensin" and related terms 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Not in Any Lists

No Comments

Negative Logits

Atsauces

-0.79

 виправивши

-0.78

ORROW

-0.60

Дереккөздер

-0.58

casian

-0.58

erals

-0.58

 previous

-0.56

 précédent

-0.56

CppMethod

-0.55

 muualla

-0.55

POSITIVE LOGITS

Ang

0.84

ANG

0.77

Ang

0.76

ANG

0.71

 ligiloj

0.70

ang

0.68

ang

0.66

 Angles

0.64

codehaus

0.60

########.

0.59

Activations Density 0.116%

references to "angiotensin" and related terms in medical contexts

No Comments

No Known Activations