INDEX

Explanations

code or programming-related syntax

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

Code, math, and form snippets

np_acts-logits-general · gemini-2.0-flash

variable assignments and declarations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 betweenstory

-1.01

 Италијани

-1.01

ArrowToggle

-0.80

 gradova

-0.79

хьтан

-0.76

RegressionTest

-0.75

Autoritní

-0.73

ьаж

-0.73

aarrggbb

-0.70

 otomatig

-0.68

POSITIVE LOGITS

\{\\

0.94

 BoxDecoration

0.80

NOPQRST

0.73

ValueStyle

0.71

存于互联网档案馆

0.69

InputBorder

0.69

CloseOperation

0.67

__(/*!

0.64

 onData

0.64

UpInside

0.63

Activations Density 17.866%

code or programming-related syntax

Code, math, and form snippets

variable assignments and declarations

No Comments

No Known Activations