INDEX

Explanations

elements of computer code and markup languages

oai_token-act-pair · gemini-2.0-flash

programming terms and syntax elements

np_token-act-pair-logits · gpt-4o-mini

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 myſelf

-1.03

 itſelf

-1.02

 himſelf

-1.02

Efq

-0.97

 themſelves

-0.97

 Jefus

-0.96

 Monfieur

-0.91

 Theſe

-0.90

 poffible

-0.89

^(@)

-0.89

POSITIVE LOGITS

0.58

0.56

les

0.52

0.50

de

0.48

kel

0.47

ac

0.46

Activations Density 3.485%

elements of computer code and markup languages

programming terms and syntax elements

code

No Comments

No Known Activations