INDEX

Explanations

phrases which contain "same", "equally", "similar", or "alike"

oai_token-act-pair · gemini-2.0-flash

same

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

الدراسه

-0.64

 صوتيه

-0.50

TestingModule

-0.48

 récol

-0.47

 ivelany

-0.47

 Ecke

-0.46

 nahilalakip

-0.45

DebuggerNonUser

-0.44

mazoo

-0.44

ValueStyle

-0.44

POSITIVE LOGITS

 समीक्षक

0.66

adaptiveStyles

0.61

httphttps

0.59

pushd

0.52

Autoritní

0.51

oneofs

0.50

 Underground

0.50

 presence

0.50

 underground

0.49

PDM

0.47

Activations Density 0.459%

phrases which contain "same", "equally", "similar", or "alike"

same

No Known Activations