INDEX

Explanations

elements and identifiers related to programming structures, particularly for defining templates and data types

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

Code, programming, or markup language elements

np_acts-logits-general · gemini-2.0-flash

code structure and attributes

np_acts-logits-general · gemini-2.5-flash-lite

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

↵↵

-0.65

↵↵↵↵

-0.52

↵↵↵

-0.50

-0.46

-0.45

↵

-0.44

<eos>

-0.41

 vuur

-0.40

 anyway

-0.39

 început

-0.38

POSITIVE LOGITS

 وتسجيلات

0.93

HtmlAttribute

0.80

 TextInputType

0.79

LayoutConstraint

0.75

 للمعارف

0.75

tvguidetime

0.74

 الدولى

0.73

AxisAlignment

0.72

IntoConstraints

0.72

 виправивши

0.71

Activations Density 0.086%

elements and identifiers related to programming structures, particularly for defining templates and data types

Code, programming, or markup language elements

code structure and attributes

No Comments

No Known Activations