INDEX

Explanations

code related to database operations and data retrieval

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

SQL database rows or results

np_acts-logits-general · gemini-2.0-flash

rows and data records

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

الإنجليزية

-0.58

ActionCreators

-0.58

SourceChecksum

-0.56

WebServlet

-0.51

Jeografia

-0.50

 CreateTagHelper

-0.50

 Diego

-0.50

ⓧ

-0.49

 Référence

-0.48

ause

-0.46

POSITIVE LOGITS

row

0.90

 rows

0.85

Row

0.81

Row

0.77

 Rows

0.77

DataRow

0.75

row

0.74

=$?

0.73

ROW

0.72

rows

0.70

Activations Density 0.119%

code related to database operations and data retrieval

SQL database rows or results

rows and data records

No Comments

No Known Activations