INDEX

Explanations

mathematical expressions and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

=""></

-0.56

}}}}

-0.51

 Besøkt

-0.49

.}}

-0.47

'>{

-0.46

UnitTesting

-0.45

 OnTriggerEnter

-0.44

]))

-0.42

"]))

-0.42

πουργ

-0.41

POSITIVE LOGITS

 الحره

0.82

RTEX

0.76

+:+

0.66

 ErrIntOverflow

0.63

 AssemblyProduct

0.61

سطس

0.61

 nakalista

0.60

出版年

0.59

DoubleQuotes

0.59

 distanciation

0.59

Activations Density 0.921%

mathematical expressions and notations

No Comments

No Known Activations