INDEX

Explanations

structures and patterns related to data types and their definitions within a programming context

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

 onAnimation

-0.59

 newArr

-0.57

 newVal

-0.53

tvguidetime

-0.50

 getID

-0.50

 IndexError

-0.49

 getCount

-0.49

 newData

-0.49

 getAddress

-0.49

 getCode

-0.48

POSITIVE LOGITS

Personendaten

0.82

[])

0.76

NameInMap

0.75

原始内容存档于

0.72

bitField

0.68

)"),

0.67

клопе

0.67

 relevant

0.65

TagMode

0.63

}</

0.62

Activations Density 0.415%

structures and patterns related to data types and their definitions within a programming context

No Comments

No Known Activations