INDEX

Explanations

phrases related to rates and their measurements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Parsons

-0.85

 Montserrat

-0.77

 pann

-0.77

 Cleary

-0.72

 McDonough

-0.70

jeg

-0.69

 Donaldson

-0.69

Tog

-0.69

avs

-0.69

../../

-0.67

POSITIVE LOGITS

 rates

1.65

 Rate

1.49

 Rates

1.48

 rate

1.47

 RATE

1.43

Rates

1.42

Rate

1.39

 RATES

1.29

RATE

1.24

rate

1.18

Activations Density 0.092%

phrases related to rates and their measurements

No Comments

No Known Activations