INDEX

Explanations

activity-related method calls within a programming context, particularly those related to view management and UI components

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

gany

-0.51

</i>

-0.49

 mergeFrom

-0.47

 case

-0.47

 shall

-0.46

**

-0.46

 péri

-0.46

))->

-0.45

us

-0.45

POSITIVE LOGITS

 findViewById

1.25

findViewById

1.03

tvguidetime

0.79

躇

0.78

tagHelperRunner

0.77

Zeneca

0.75

 doubtnut

0.74

 houſe

0.72

ſelf

0.70

WEBPACK

0.69

Activations Density 0.023%

activity-related method calls within a programming context, particularly those related to view management and UI components

No Comments

No Known Activations