INDEX

Explanations

repetitive elements or patterns in numerical data or coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Datuak

-0.95

 AssemblyCulture

-0.92

TRIBUN

-0.80

enumii

-0.79

ArrowToggle

-0.79

ⓧ

-0.79

tagHelper

-0.77

WriteAttribute

-0.77

 initComponents

-0.76

QRect

-0.75

POSITIVE LOGITS

TestingModule

0.48

 hefyd

0.42

↵

0.41

CreateModel

0.38

dis

0.38

0.37

ActionMode

0.37

 invokingState

0.36

Activations Density 0.055%

repetitive elements or patterns in numerical data or coding structures

No Comments

No Known Activations