INDEX

Explanations

various types of closing parentheses and brackets used in code

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

Code or equations, especially parentheses

np_acts-logits-general · gemini-2.0-flash

code blocks and user input

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

LookAnd

-0.93

AddTagHelper

-0.90

𑄮

-0.84

<unused17>

-0.83

<unused41>

-0.83

<unused79>

-0.82

 témoig

-0.82

<unused74>

-0.82

<unused16>

-0.82

<unused52>

-0.82

POSITIVE LOGITS

 there

0.50

we

0.47

 they

0.43

it

0.43

0.42

 NSCoder

0.40

 then

0.36

 means

0.35

 thì

0.35

 ciascuno

0.35

Activations Density 0.088%

various types of closing parentheses and brackets used in code

Code or equations, especially parentheses

code blocks and user input

No Comments

No Known Activations