INDEX

Explanations

documentation-style annotations and summaries in code

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

Code initialization or references

np_acts-logits-general · gemini-2.0-flash

InitializeComponent, DataAnnotations, Last, phonon, nitric

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

tipation

-0.61

ukah

-0.58

+#+#

-0.54

guous

-0.54

nemia

-0.54

RegressionTest

-0.53

mybatisplus

-0.53

liesslich

-0.52

missão

-0.51

 olvid

-0.51

POSITIVE LOGITS

contentLoaded

0.94

disposing

0.91

IContainer

0.75

 Dispose

0.74

 ExecuteAsync

0.62

 Required

0.61

ComponentModel

0.60

 disposing

0.57

MenuInflater

0.56

 trai

0.56

Activations Density 0.077%

documentation-style annotations and summaries in code

Code initialization or references

InitializeComponent, DataAnnotations, Last, phonon, nitric

No Comments

No Known Activations