INDEX

Explanations

specific references to numerical or technical classifications, particularly related to "CS" and associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

+#+#

-0.93

Composable

-0.89

 Gorman

-0.81

 Boeh

-0.80

甸

-0.79

abetes

-0.78

GeneratedValue

-0.74

Ug

-0.73

Gor

-0.73

 McKinnon

-0.72

POSITIVE LOGITS

'{@

0.77

 Oakes

0.75

 Cabral

0.68

sweep

0.67

ستاگرام

0.66

 sweeps

0.65

anément

0.65

CS

0.64

Lung

0.64

 eagle

0.63

Activations Density 0.884%

specific references to numerical or technical classifications, particularly related to "CS" and associated terms

No Comments

No Known Activations