INDEX

Explanations

specific medical terminology and references related to tumors and glandular anatomy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Jaco

-0.94

NEO

-0.83

Pom

-0.82

Portale

-0.82

COA

-0.82

FormState

-0.79

 Jasmin

-0.79

InjectAttribute

-0.77

 Edson

-0.76

 Esau

-0.76

POSITIVE LOGITS

Loch

0.82

lisi

0.79

 Catania

0.79

 Unger

0.78

 africain

0.76

 Luzern

0.75

 Parisi

0.75

 Landis

0.74

olig

0.73

 tapa

0.72

Activations Density 2.256%

specific medical terminology and references related to tumors and glandular anatomy

No Comments

No Known Activations