INDEX

Explanations

elements associated with width, height, and calculations involving dimensions or coordinates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

SequentialGroup

-0.79

ParallelGroup

-0.51

();)

-0.49

AccessorTable

-0.48

chowy

-0.46

 sapp

-0.46

ástico

-0.45

ásticos

-0.45

helves

-0.44

enet

-0.44

POSITIVE LOGITS

 متعلقه

0.68

ImageContext

0.64

المكان

0.60

دانشنامهٔ

0.59

mybatisplus

0.58

 Normdatei

0.58

TypedDataSet

0.58

WebVitals

0.57

HomeAsUpEnabled

0.56

 Commencez

0.56

Activations Density 0.210%

elements associated with width, height, and calculations involving dimensions or coordinates

No Comments

No Known Activations