INDEX

Explanations

code-related elements and functions associated with creating and managing product tags and responses

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

Followed by a period

np_acts-logits-general · gemini-2.0-flash

code object names

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

Izvori

-0.64

endpush

-0.63

diyesi

-0.57

transQ

-0.57

 gradova

-0.57

LookAnd

-0.55

ьаж

-0.54

SharedModule

-0.54

ClassNotFound

-0.53

conio

-0.52

POSITIVE LOGITS

 also

0.83

 alſo

0.81

also

0.70

Also

0.67

 ALSO

0.60

addPreferredGap

0.60

 Also

0.59

[*]

0.58

 también

0.58

Activations Density 0.083%

code-related elements and functions associated with creating and managing product tags and responses

Followed by a period

code object names

No Comments

No Known Activations