INDEX

Explanations

commands and navigation steps in code or scripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

eradish

-0.54

CGContext

-0.52

llium

-0.44

boxShadow

-0.44

 awakeFromNib

-0.43

cupine

-0.42

 palk

-0.42

shadowOpacity

-0.42

 sympy

-0.42

 Mustangs

-0.41

POSITIVE LOGITS

SceneManagement

1.11

sendRedirect

0.97

navigate

0.89

 useRouter

0.83

contentLoaded

0.81

 للاسماء

0.77

 Navigate

0.75

StoryboardSegue

0.73

pushd

0.73

 ModelAndView

0.73

Activations Density 0.269%

commands and navigation steps in code or scripts

No Comments

No Known Activations

commands and navigation steps in code or scripts

No Comments

No Known Activations