INDEX

Explanations

technical terms related to vector and matrix data structures in programming

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

"Vector" token

np_acts-logits-general · gemini-2.0-flash

vector types and dimensions

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

mappedBy

-0.62

perger

-0.53

EndGlobalSection

-0.52

Committee

-0.48

TOXIC

-0.48

tomation

-0.46

 getRole

-0.45

 متعلقه

-0.45

BeforeClass

-0.44

limus

-0.44

POSITIVE LOGITS

ial

0.82

ized

0.65

TagMode

0.61

AccessorTable

0.61

ially

0.61

Xd

0.57

WriteTagHelper

0.56

IAL

0.56

 externi

0.55

cardio

0.55

Activations Density 0.115%

technical terms related to vector and matrix data structures in programming

"Vector" token

vector types and dimensions

No Comments

No Known Activations