INDEX

Explanations

references to stamps, particularly in a crafting or documentation context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

AxisAlignment

-0.73

出版年

-0.71

 Walkover

-0.68

DockStyle

-0.67

bitField

-0.66

Демографія

-0.66

 nevoie

-0.62

libft

-0.61

 verfü

-0.59

 Италијани

-0.59

POSITIVE LOGITS

bibfield

0.66

 whoſe

0.64

LLAB

0.64

bibinfo

0.60

operatorname

0.60

ſelf

0.59

 stamp

0.58

liminaries

0.57

EFIAPI

0.57

 متعلقه

0.56

Activations Density 0.133%

references to stamps, particularly in a crafting or documentation context

No Comments

No Known Activations