INDEX

Explanations

terms related to orientation and spatial arrangement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

())));

-0.66

 tartalomajánló

-0.61

thâu

-0.59

IBLES

-0.59

]){

-0.57

guardo

-0.56

{};

-0.56

Res

-0.56

}}$\\

-0.55

')));

-0.55

POSITIVE LOGITS

 size

0.96

size

0.82

 SIZE

0.79

Size

0.79

 diameter

0.77

 Size

0.77

 sizes

0.73

SIZE

0.73

 taille

0.70

Adult

0.70

Activations Density 0.170%

terms related to orientation and spatial arrangement

No Comments

No Known Activations