INDEX

Explanations

references to large quantities or sizes, particularly in relation to objects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 monnaie

-0.52

 estrecha

-0.52

 étroite

-0.49

 étro

-0.49

 tighter

-0.48

 meilleurs

-0.48

 achar

-0.47

 légère

-0.47

τως

-0.46

PyTuple

-0.45

POSITIVE LOGITS

big

1.28

 giant

1.25

 gigantic

1.18

BIG

1.14

 large

1.12

giant

1.10

big

1.08

Big

1.07

Giant

1.07

 giants

1.05

Activations Density 0.726%

references to large quantities or sizes, particularly in relation to objects or concepts

No Comments

No Known Activations