INDEX

Explanations

various numerical values and symbols indicating programming or mathematical operations

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

Бахар

-0.68

expandindo

-0.67

ArgsConstructor

-0.67

migrationBuilder

-0.65

 للمعارف

-0.64

ScopeManager

-0.60

 الحره

-0.60

UnsafeEnabled

-0.59

קישורים

-0.59

POSITIVE LOGITS

1.80

+,

1.59

+.

1.41

+)

1.40

+/

1.39

++

1.31

+:

1.26

+'

1.24

+"

1.23

 Plus

1.21

Activations Density 0.608%

various numerical values and symbols indicating programming or mathematical operations

No Comments

No Known Activations