INDEX

Explanations

phrasings and patterns related to function definitions in programming

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

Code snippets/fragments

np_acts-logits-general · gemini-2.0-flash

handles return statements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 فريبيس

-0.65

omiast

-0.59

Và

-0.58

жели

-0.58

จึง

-0.55

---|---|

-0.55

}}}

-0.54

 therefore

-0.53

notifyListeners

-0.53

큼

-0.53

POSITIVE LOGITS

throw

0.90

 Waray

0.76

VersionUID

0.73

 fallu

0.68

"""

0.64

fatalError

0.64

"""

0.63

pass

0.61

paravant

0.59

Билгалдахарш

0.58

Activations Density 0.139%

phrasings and patterns related to function definitions in programming

Code snippets/fragments

handles return statements

No Comments

No Known Activations