INDEX

Explanations

high-frequency or significant mathematical constants related to functions in theoretical contexts

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

 Normdatei

-0.89

 photolibrary

-0.87

 myſelf

-0.86

Efq

-0.85

 Theſe

-0.84

 Beſ

-0.84

ArgsConstructor

-0.83

 ſind

-0.82

 Jefus

-0.81

 itſelf

-0.80

POSITIVE LOGITS

Omega

0.72

wiki

0.70

mah

0.59

 ultimate

0.58

 quasi

0.58

Mah

0.54

master

0.53

 quam

0.52

 infrastructure

0.51

 existence

0.51

Activations Density 0.199%

high-frequency or significant mathematical constants related to functions in theoretical contexts

No Comments

No Known Activations