INDEX

Explanations

mathematical notation and formulas related to sequences and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MainAxisSize

-0.77

setVerticalGroup

-0.74

">//

-0.72

脚注の使い方

-0.72

-0.71

])){

-0.69

__*/

-0.69

 estekak

-0.68

 resourceCulture

-0.67

)++;

-0.67

POSITIVE LOGITS

for

0.56

írito

0.52

Brought

0.51

Jîn

0.49

 urmă

0.49

 dieux

0.49

SBATCH

0.48

 vulga

0.48

 noastre

0.47

 individuales

0.46

Activations Density 1.117%

mathematical notation and formulas related to sequences and functions

No Comments

No Known Activations