INDEX

Explanations

terms related to performance measurement and improvement

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

czy

-0.51

bootstrapcdn

-0.50

@[+][

-0.50

TargetException

-0.49

moveToFirst

-0.48

BASEPATH

-0.48

 мѣ

-0.48

UTUP

-0.48

IActionResult

-0.47

ogados

-0.46

POSITIVE LOGITS

+#+#

0.68

Served

0.56

DoubleQuotes

0.55

}{*}{

0.53

 препратки

0.53

served

0.52

 hoor

0.51

 Served

0.51

Ծանոթ

0.51

IONAL

0.51

Activations Density 0.479%

terms related to performance measurement and improvement

No Comments

No Known Activations