INDEX

Explanations

technical terms related to electronics and computing

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

before error messages

np_acts-logits-general · gemini-2.0-flash

error messages, popups, or displays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Мексичка

-0.59

ANTLR

-0.59

DockStyle

-0.59

 wireType

-0.58

shadowRadius

-0.56

itability

-0.55

XDECREF

-0.53

StoryboardSegue

-0.53

Portale

-0.52

contentLoaded

-0.52

POSITIVE LOGITS

 prompt

0.97

pop

0.97

 displayed

0.94

 prompts

0.91

 popup

0.90

 message

0.83

提示

0.83

 screen

0.81

 pops

0.81

 display

0.80

Activations Density 0.374%

technical terms related to electronics and computing

before error messages

error messages, popups, or displays

No Comments

No Known Activations