INDEX

Explanations

medical terms related to measurements and quantities within studies

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

Not in Any Lists

No Comments

Negative Logits

igo

-0.49

-0.48

-0.47

og

-0.46

As

-0.46

-0.45

Po

-0.45

-0.44

Ab

-0.44

POSITIVE LOGITS

 bezeichneter

0.97

ंदीखरीदारी

0.96

RenderAtEndOf

0.89

 protoimpl

0.80

Datuak

0.80

 ISNI

0.79

GEBURTSDATUM

0.79

UnsafeEnabled

0.77

 للمعارف

0.77

 nakalista

0.76

Activations Density 1.056%

medical terms related to measurements and quantities within studies

No Comments

No Known Activations