INDEX

Explanations

instructions related to control flow and iteration in programming

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

"i" in "for" loops

np_acts-logits-general · gemini-2.0-flash

programming loop index 'i'

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

]++;

-0.64

textEdit

-0.52

mbol

-0.51

forma

-0.51

IMENTS

-0.50

ніципалі

-0.50

енча

-0.49

hower

-0.49

hanger

-0.49

cripted

-0.48

POSITIVE LOGITS

featureID

0.73

NSIndexPath

0.68

 IndexPath

0.65

 CreateTagHelper

0.63

stddef

0.61

 للمعارف

0.59

offsetof

0.57

postIndex

0.56

NOPQRST

0.52

GraphicsUnit

0.52

Activations Density 0.338%

instructions related to control flow and iteration in programming

"i" in "for" loops

programming loop index 'i'

No Comments

No Known Activations