INDEX

Explanations

phrases related to yielding or a loss of control

oai_token-act-pair · gemini-2.0-flash

politics and concessions

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

 ujednoznacz

-0.98

 nahilalakip

-0.85

 disambiguazione

-0.76

parsedMessage

-0.74

IndentedString

-0.73

httphttps

-0.73

 שוליים

-0.69

ThroughAttribute

-0.68

CppMethod

-0.66

WebVitals

-0.66

POSITIVE LOGITS

 défaite

0.55

 debole

0.50

AnimationsModule

0.50

ruitt

0.49

signs

0.47

ierzch

0.45

NullException

0.45

Publica

0.45

 sanitaires

0.45

 envers

0.45

Activations Density 0.539%

phrases related to yielding or a loss of control

politics and concessions

No Comments

No Known Activations