INDEX

Explanations

programming constructs associated with conditional checks and error handling

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

Keywords followed by control flow statements

np_acts-logits-general · gemini-2.0-flash

return or throw

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

MigrationBuilder

-0.67

Демографія

-0.66

WireFormatLite

-0.65

spyOn

-0.60

drawSprites

-0.59

 مشين

-0.58

 elseif

-0.57

=$?

-0.57

 doInBackground

-0.56

fjspx

-0.55

POSITIVE LOGITS

throw

1.61

 throw

1.15

raise

1.05

return

0.87

continue

0.78

goto

0.77

 Throw

0.73

 return

0.70

 raise

0.69

panic

0.67

Activations Density 0.099%

programming constructs associated with conditional checks and error handling

Keywords followed by control flow statements

return or throw

No Comments

No Known Activations