INDEX

Explanations

medical abbreviations and their definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

↵↵

-0.54

<eos>

-0.51

al

-0.49

<strong>

-0.48

--

-0.47

-0.46

by

-0.46

ytte

-0.46

 vicenda

-0.46

POSITIVE LOGITS

httphttps

0.90

 autorytatywna

0.88

awtextra

0.85

=$?

0.82

QMetaType

0.80

Efq

0.78

EndGlobalSection

0.78

RegressionTest

0.75

Hentet

0.72

nloa

0.71

Activations Density 0.803%

medical abbreviations and their definitions

No Comments

No Known Activations