INDEX

Explanations

technical terms related to assembly, linking processes, and compiler flags within a programming context

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

Executable files or binaries

np_acts-logits-general · gemini-2.0-flash

compiled executables and binaries

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

posedge

-0.74

 metav

-0.71

complexType

-0.64

findpost

-0.62

ี่ยน

-0.60

NOPQRST

-0.60

 Wallflower

-0.55

estor

-0.54

StructEnd

-0.53

casio

-0.52

POSITIVE LOGITS

 compiled

0.90

 executable

0.89

 binary

0.85

 execu

0.82

 binaries

0.76

binary

0.73

 runtime

0.73

compiled

0.69

 execution

0.68

Executable

0.68

Activations Density 0.856%

technical terms related to assembly, linking processes, and compiler flags within a programming context

Executable files or binaries

compiled executables and binaries

No Comments

No Known Activations