INDEX

Explanations

variables and parameters used within API calls and data handling

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

Code snippets with data or body

np_acts-logits-general · gemini-2.0-flash

request arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

endphp

-0.63

NameInMap

-0.45

AddTagHelper

-0.43

richTextPanel

-0.43

новништво

-0.42

TagMode

-0.41

greenrobot

-0.40

 clearColor

-0.40

꜆

-0.40

kijken

-0.40

POSITIVE LOGITS

LabelTagHelper

0.51

ModelForm

0.50

TextWatcher

0.47

submitted

0.47

setupUi

0.45

 submitted

0.45

 declarations

0.44

 ब्रेकडाउन

0.43

gut

0.43

囗

0.41

Activations Density 0.085%

variables and parameters used within API calls and data handling

Code snippets with data or body

request arguments

No Comments

No Known Activations