INDEX

Explanations

language related to government finances

oai_token-act-pair · gemini-2.0-flash

foreign words or terms

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

Seeking authorization

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

QMetaType

-0.86

">//

-0.73

 Shakspeare

-0.70

 متعلقه

-0.69

DockStyle

-0.68

expandindo

-0.67

 pinulongan

-0.64

 ainfi

-0.63

 blest

-0.63

 Matériau

-0.62

POSITIVE LOGITS

nod

0.51

self

0.50

ela

0.46

ῖν

0.45

emp

0.45

Nor

0.45

exitRule

0.44

льников

0.43

kok

0.42

 fait

0.42

Activations Density 0.993%

language related to government finances

foreign words or terms

Seeking authorization

No Comments

No Known Activations