INDEX

Explanations

terms related to subtypes and classifications in biomedical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

évaluateur

-0.73

RegressionTest

-0.71

principalColumn

-0.70

 <<<<<<<<<<<<<<

-0.69

+#+#

-0.67

WebElementEntity

-0.67

 protoimpl

-0.64

 Signalez

-0.63

JspWriter

-0.63

 للمعارف

-0.63

POSITIVE LOGITS

Pav

0.39

별

0.38

pri

0.37

 different

0.36

 shapes

0.36

subtype

0.35

 lựa

0.35

Bins

0.34

 diferentes

0.34

Nor

0.33

Activations Density 1.343%

terms related to subtypes and classifications in biomedical contexts

No Comments

No Known Activations