INDEX

Explanations

references to research articles and their metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

ContentAlignment

-0.59

 tartalomajánló

-0.59

AccessorTable

-0.49

دانشنامهٔ

-0.49

 witnesses

-0.48

 Oakley

-0.48

 fevere

-0.48

={<

-0.47

XtraReports

-0.47

ícios

-0.45

POSITIVE LOGITS

 nonatomic

0.77

nonatomic

0.74

satunya

0.67

MENAFN

0.63

quiries

0.58

 للمعارف

0.58

Przypisy

0.58

//

0.58

igshid

0.57

writeField

0.57

Activations Density 0.074%

references to research articles and their metadata

No Comments

No Known Activations