INDEX

Explanations

references to particular food items

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 Paglinawan

-0.64

 wineries

-0.61

verwijspagina

-0.61

مصادر

-0.61

 BoxFit

-0.61

 wine

-0.60

 sherry

-0.60

yntaxException

-0.60

 linens

-0.59

+:+

-0.59

POSITIVE LOGITS

 McDonald

0.86

 burger

0.85

 McDonalds

0.79

McDonald

0.78

 burgers

0.77

 franchise

0.75

 fast

0.74

InjectAttribute

0.74

 fries

0.74

🍔

0.74

Activations Density 0.116%

references to particular food items

No Comments

No Known Activations