INDEX

Explanations

words and phrases referring to logical implications, constraints, and making something happen

oai_token-act-pair · gemini-2.0-flash

verbs/verb endings

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 protoimpl

-0.53

jspx

-0.52

regelen

-0.50

 Roskov

-0.47

hands

-0.46

 doInBackground

-0.46

 panahon

-0.45

ктан

-0.45

 teck

-0.44

{};

-0.43

POSITIVE LOGITS

 HasFactory

0.63

]")]

0.59

(&:

0.53

 pensioners

0.52

UserScript

0.52

 Мексичка

0.51

SceneManagement

0.51

CharStream

0.50

íncia

0.49

 ویکی‌پدیای

0.49

Activations Density 1.644%

words and phrases referring to logical implications, constraints, and making something happen

verbs/verb endings

No Comments

No Known Activations