INDEX

Explanations

sections of code or programming constructs

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

Code or data snippets

np_acts-logits-general · gemini-2.0-flash

return if

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

Personendaten

-0.52

 مرئيه

-0.52

ThroughAttribute

-0.51

enderror

-0.50

PerformLayout

-0.48

GenerationType

-0.46

ждую

-0.45

 مواليد

-0.43

 ngũ

-0.41

 sebou

-0.41

POSITIVE LOGITS

Джерела

0.64

SOUNDBITE

0.63

eradish

0.61

addCriterion

0.60

 Архивировано

0.57

CloseOperation

0.56

DebuggerStep

0.55

 consultato

0.55

 joaat

0.55

Spoljašnje

0.55

Activations Density 0.061%

sections of code or programming constructs

Code or data snippets

return if

No Comments

No Known Activations