INDEX

Explanations

mathematical notations and expressions related to probabilities and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.76

Diwedd

-0.61

دانشنامهٔ

-0.60

LookAnd

-0.57

 فريبيس

-0.56

 Shakspeare

-0.56

HostException

-0.55

లాలు

-0.54

 perciò

-0.53

 ModelExpression

-0.53

POSITIVE LOGITS

 left

0.67

 math

0.58

 operator

0.56

 display

0.54

lib

0.53

perator

0.53

 Operator

0.51

 Display

0.51

}}}}

0.51

 Left

0.50

Activations Density 0.745%

mathematical notations and expressions related to probabilities and statistics

No Comments

No Known Activations