INDEX

Explanations

terms and concepts related to various diseases and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 acrí

-0.51

 Schulter

-0.45

waypoint

-0.44

 Wren

-0.42

 Mano

-0.42

 Ufer

-0.41

 späteren

-0.41

 Stirn

-0.41

余

-0.40

 beurre

-0.40

POSITIVE LOGITS

 disease

0.88

 Disease

0.84

Disease

0.81

 diseases

0.81

disease

0.76

 infection

0.76

 illness

0.75

 ziekte

0.74

 Illness

0.72

 Diseases

0.71

Activations Density 0.379%

terms and concepts related to various diseases and their effects

No Comments

No Known Activations