INDEX

Explanations

words and phrases indicating that a character is powerful and/or is being defeated and/or killed.

oai_token-act-pair · gemini-2.0-flash

character defeat and destruction

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 continúas

-0.56

-0.54

 citoy

-0.54

closedir

-0.52

 inconn

-0.51

 macchine

-0.50

Efq

-0.49

ModelBuilder

-0.47

 téléph

-0.47

 ucapnya

-0.46

POSITIVE LOGITS

 propOrder

0.61

 الرياضيه

0.61

StoreMessageInfo

0.60

oneofs

0.60

AlterField

0.60

FormTagHelper

0.59

 kaynağından

0.58

 AttributeSet

0.57

:✨

0.57

onAttach

0.56

Activations Density 1.118%

words and phrases indicating that a character is powerful and/or is being defeated and/or killed.

character defeat and destruction

No Comments

No Known Activations