INDEX

Explanations

code snippets, especially python ones including print statements, file operations, and potentially some shell commands

oai_token-act-pair · gemini-2.0-flash

print/log statements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

awtextra

-0.52

 Diplomatic

-0.49

 zusammenge

-0.49

 philanthrop

-0.46

 forgiven

-0.45

 digestible

-0.45

 parche

-0.45

``

-0.45

<h6>

-0.45

POSITIVE LOGITS

sidemargin

0.69

rungsseite

0.65

GEBURTSDATUM

0.65

Билгалдахарш

0.65

photobucket

0.62

('');

0.62

 EconPapers

0.60

UnusedPrivate

0.60

 Wikimedijinoj

0.58

انيف

0.58

Activations Density 10.488%

code snippets, especially python ones including print statements, file operations, and potentially some shell commands

print/log statements

No Comments

No Known Activations