INDEX

Explanations

symbols and formatting specific to mathematical or scientific text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Shakspeare

-1.02

 myſelf

-0.97

 itſelf

-0.91

 ―――――

-0.90

 الرياضيه

-0.87

 ་་

-0.86

]";

-0.84

)*/

-0.83

 Phry

-0.81

 }}$}

-0.81

POSITIVE LOGITS

.~\

0.71

 auto

0.68

 neutron

0.66

 estimés

0.61

 http

0.60

.~(\

0.58

0.56

 established

0.55

auto

0.54

ki

0.53

Activations Density 0.583%

symbols and formatting specific to mathematical or scientific text

No Comments

No Known Activations