INDEX

Explanations

technical terms and constructs related to programming functions and parameters

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

adaptiveStyles

-0.60

قایناقلار

-0.51

Obrázky

-0.47

WithIOException

-0.44

IntoConstraints

-0.43

tvguidetime

-0.43

 onCancelled

-0.42

EditorBrowsable

-0.42

 achieved

-0.41

 springfox

-0.41

POSITIVE LOGITS

 arguments

2.03

 argument

1.86

arguments

1.76

 Arguments

1.73

 args

1.68

Arguments

1.68

arg

1.68

Argument

1.67

argument

1.67

 Argument

1.65

Activations Density 0.625%

technical terms and constructs related to programming functions and parameters

No Comments

No Known Activations