INDEX

Explanations

mentions of medical topics and healthcare-related terms

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

躇

-1.03

onAttach

-0.88

Izvori

-0.84

TypedDataSet

-0.83

 MessageBoxIcon

-0.80

SBATCH

-0.79

IsContent

-0.75

quirrels

-0.74

ConstraintMaker

-0.73

alitions

-0.72

POSITIVE LOGITS

 Medical

1.04

 medical

1.02

Medical

0.92

medic

0.90

 MEDICAL

0.88

мед

0.88

medical

0.87

MEDICAL

0.82

 medicine

0.82

 doctors

0.82

Activations Density 0.100%

mentions of medical topics and healthcare-related terms

No Comments

No Known Activations