INDEX

Explanations

mathematical notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

fjspx

-0.67

 disambiguazione

-0.67

isto

-0.67

 propOrder

-0.66

Personensuche

-0.61

 nakalista

-0.60

 EconPapers

-0.58

printStackTrace

-0.58

hdashline

-0.57

ⓧ

-0.57

POSITIVE LOGITS

$|\

0.93

$|

0.92

|\

0.90

>|</

0.90

=|

0.89

}{||

0.82

{|

0.79

$|

0.78

)|\

0.77

ISupport

0.74

Activations Density 0.534%

mathematical notation and symbols

No Comments

No Known Activations