INDEX

Explanations

references to web driver and element-finding strategies in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 odkazy

-0.77

 للمعارف

-0.75

 estekak

-0.74

 مشين

-0.74

Демографія

-0.74

Personendaten

-0.72

 تضيفلها

-0.72

EndContext

-0.67

StructEnd

-0.66

DeleteBehavior

-0.64

POSITIVE LOGITS

css

0.59

xpath

0.50

ByExample

0.47

Css

0.47

CSS

0.42

id

0.42

 esteja

0.41

partial

0.41

Partial

0.41

สู

0.41

Activations Density 0.104%

references to web driver and element-finding strategies in programming

No Comments

No Known Activations