INDEX

Explanations

terms related to medical procedures and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

leneck

-0.55

}{*}{

-0.49

,:);

-0.49

avía

-0.49

 Bancroft

-0.47

])).

-0.46

fieldLabel

-0.46

 CONV

-0.45

“”

-0.45

JPL

-0.45

POSITIVE LOGITS

ViewFeatures

0.96

 оригіналу

0.85

ValueStyle

0.79

 Mari

0.78

mari

0.77

rungsseite

0.76

EndGlobalSection

0.76

mar

0.75

HasAnnotation

0.74

MAR

0.73

Activations Density 2.948%

terms related to medical procedures and terminology

No Comments

No Known Activations