INDEX

Explanations

SQL commands and syntax

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

SQL code snippets

np_acts-logits-general · gemini-2.0-flash

SQL SELECT statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 EconPapers

-0.69

 lenker

-0.60

Gön

-0.54

Datuak

-0.53

::$_

-0.53

ără

-0.53

]-->

-0.52

AtIndexPath

-0.52

 مشين

-0.52

stanti

-0.51

POSITIVE LOGITS

ftagPool

0.61

يكب

0.54

 XXIII

0.54

EDEFAULT

0.48

例文

0.46

Karten

0.45

izzera

0.44

oneofs

0.44

érature

0.44

 XIII

0.43

Activations Density 0.052%

SQL commands and syntax

SQL code snippets

SQL SELECT statements

No Comments

No Known Activations