INDEX

Explanations

phrases that include a specific article followed by nouns or descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ThroughAttribute

-0.87

 ExecuteAsync

-0.86

ImageContext

-0.79

RectangleBorder

-0.77

makeConstraints

-0.76

 Unwin

-0.73

 PopupWindow

-0.71

waitKey

-0.69

IUrlHelper

-0.69

irvana

-0.68

POSITIVE LOGITS

 very

0.79

is

0.71

 also

0.70

 extremely

0.67

 really

0.62

 unique

0.60

 most

0.59

 pretty

0.58

 actually

0.57

 complex

0.57

Activations Density 0.198%

phrases that include a specific article followed by nouns or descriptors

No Comments

No Known Activations