INDEX

Explanations

SQL database queries containing "SELECT", "FROM", and date information, often involving "ORDER BY" and "UNION ALL" commands

oai_token-act-pair · gemini-2.0-flash

select

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.18

 myſelf

-1.16

Efq

-1.11

 Monfieur

-1.09

 Majefty

-1.09

ſelves

-1.08

 Houſe

-1.06

 Anſ

-1.06

 faſt

-1.06

 Theſe

-1.05

POSITIVE LOGITS

0.68

0.67

0.58

0.55

0.54

<eos>

0.54

0.53

Activations Density 4.620%

SQL database queries containing "SELECT", "FROM", and date information, often involving "ORDER BY" and "UNION ALL" commands

select

No Comments

No Known Activations