INDEX

Explanations

sentences containing strong medical or clinical terminologies, particularly those that indicate results or characteristics of studies or conditions

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

GTCX

-0.68

PYX

-0.51

CppMethod

-0.47

haften

-0.47

RTEE

-0.46

 Biôgrafia

-0.45

:+:

-0.45

 Audiodateien

-0.45

новништво

-0.44

Parcelize

-0.44

POSITIVE LOGITS

transQ

0.49

 ویکی‌پدیا

0.47

 nonUne

0.46

белый

0.41

HomeAsUpEnabled

0.41

เภ

0.39

 Prov

0.38

currentColor

0.38

IContainer

0.37

hom

0.34

Activations Density 0.388%

sentences containing strong medical or clinical terminologies, particularly those that indicate results or characteristics of studies or conditions

No Comments

No Known Activations