INDEX

Explanations

references to py-related terms and concepts, particularly in scientific contexts

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

DockStyle

-0.87

новниш

-0.86

CloseOperation

-0.76

interopRequire

-0.76

GEBURTS

-0.76

lapsingToolbar

-0.74

 MainAxisSize

-0.74

 InputDecoration

-0.74

addPreferredGap

-0.71

ReactDOM

-0.70

POSITIVE LOGITS

Py

0.86

py

0.73

Py

0.67

 PyObject

0.63

PY

0.60

PY

0.51

py

0.49

jsx

0.46

jamas

0.46

pys

0.45

Activations Density 0.134%

references to py-related terms and concepts, particularly in scientific contexts

No Comments

No Known Activations