INDEX

Explanations

references to images or pictures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ConstraintMaker

-0.98

SBATCH

-0.97

olesale

-0.97

juvant

-0.94

EDEFAULT

-0.93

horabuena

-0.92

GIVEREF

-0.87

maiden

-0.87

/>";

-0.87

principalColumn

-0.86

POSITIVE LOGITS

 picture

1.58

 pictures

1.52

 Picture

1.44

picture

1.39

 Pictures

1.37

Picture

1.33

 PICTURE

1.33

PICTURE

1.28

pictures

1.28

Pictures

1.20

Activations Density 0.045%

references to images or pictures

No Comments

No Known Activations