INDEX

Explanations

mathematical equations and notations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

postIndex

-0.74

WebVitals

-0.71

TextHelper

-0.64

sizeCache

-0.63

EndTag

-0.63

IndentedString

-0.62

GraphicsUnit

-0.62

DeleteBehavior

-0.59

 ErrIntOverflow

-0.54

Tē

-0.53

POSITIVE LOGITS

 BoxDecoration

0.57

 дву

0.52

流

0.51

tigung

0.50

Two

0.50

②

0.50

 Instrum

0.48

IMAN

0.47

TWO

0.47

Activations Density 0.717%

mathematical equations and notations

No Comments

No Known Activations