INDEX

Explanations

measurements and quantities in cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 marche

-0.69

 Rutgers

-0.66

 Rockford

-0.64

rungsseite

-0.63

 disponibilités

-0.62

 Burgos

-0.61

anais

-0.61

 Kiel

-0.59

 Newark

-0.58

знес

-0.57

POSITIVE LOGITS

cup

2.97

Cup

2.84

 cups

2.77

cup

2.62

CUP

2.60

 Cups

2.58

Cup

2.56

cups

2.23

CUP

2.14

杯

1.68

Activations Density 0.033%

measurements and quantities in cooking instructions

No Comments

No Known Activations