INDEX

Explanations

specific terms related to medical or scientific concepts, particularly in the realm of health and treatment

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

 Coch

-0.98

 Ralf

-0.87

 Recep

-0.85

 Schlu

-0.82

 Plaid

-0.82

 Schalke

-0.77

 Czer

-0.77

Randall

-0.77

 chutes

-0.76

 ../../

-0.74

POSITIVE LOGITS

 թվական

0.85

 Foxx

0.85

Pag

0.85

 Arora

0.83

 Twig

0.82

Gigi

0.80

 Berger

0.79

 propOrder

0.78

INCREF

0.77

 Lawson

0.77

Activations Density 2.525%

specific terms related to medical or scientific concepts, particularly in the realm of health and treatment

No Comments

No Known Activations