INDEX

Explanations

technical terms and abbreviations related to health and medical measurements

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

basicConfig

-0.64

новниш

-0.57

afficheront

-0.57

Filmographie

-0.55

WebVitals

-0.55

الإنجليزية

-0.54

 RIPRODUZIONE

-0.52

ագրություններ

-0.52

öffentlichungen

-0.51

 myſelf

-0.51

POSITIVE LOGITS

TU

1.05

TI

1.03

TA

1.03

Tu

1.01

TD

1.00

 Tess

0.99

TMC

0.99

tu

0.98

ti

0.97

TE

0.97

Activations Density 1.710%

technical terms and abbreviations related to health and medical measurements

No Comments

No Known Activations