INDEX

Explanations

terms related to food and meals

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

 Lori

-0.58

 Harg

-0.58

Lori

-0.57

 Dumont

-0.57

 Oxfordshire

-0.55

 Huddersfield

-0.55

 Lindley

-0.54

 Humphries

-0.54

 محفوظة

-0.54

 Shropshire

-0.54

POSITIVE LOGITS

ea

0.69

Nea

0.60

eak

0.58

eah

0.57

 PEAR

0.54

Kea

0.53

Pea

0.52

Lean

0.52

Sea

0.52

Tea

0.52

Activations Density 0.607%

terms related to food and meals

No Comments

No Known Activations