INDEX

Explanations

terms and concepts related to definitions and measurements in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Clik

-0.86

 utafitiHapana

-0.74

 فريبيس

-0.74

MigrationBuilder

-0.69

 nakalista

-0.67

 समीक्षक

-0.66

 للمعارف

-0.63

IntoConstraints

-0.62

KommentareTeilen

-0.60

 doInBackground

-0.58

POSITIVE LOGITS

AsUp

0.42

 often

0.41

corazón

0.38

 commonly

0.36

 usually

0.36

 Often

0.35

often

0.35

班

0.34

 generally

0.34

 souvent

0.33

Activations Density 0.864%

terms and concepts related to definitions and measurements in scientific contexts

No Comments

No Known Activations