INDEX

Explanations

medical terms and related concepts, particularly those associated with health conditions and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Schwan

-0.82

 Stearns

-0.78

 laurel

-0.78

 Pasquale

-0.78

 sandals

-0.78

 Crete

-0.77

 Herren

-0.76

 vertes

-0.76

 Calabria

-0.75

 SHAPE

-0.72

POSITIVE LOGITS

RTLR

0.91

Становништво

0.90

ypsies

0.84

etheless

0.83

atmos

0.81

ñoz

0.78

 ApiResponse

0.77

cektir

0.76

riors

0.76

LIT

0.75

Activations Density 8.925%

medical terms and related concepts, particularly those associated with health conditions and procedures

No Comments

No Known Activations