INDEX

Explanations

the word "injury" and related terms like "non-"

oai_token-act-pair · gemini-2.0-flash

injury

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

IVEREF

-0.85

bootstrapcdn

-0.81

المكان

-0.81

thâu

-0.80

IsMutable

-0.79

 gynhyrchwyd

-0.76

OGND

-0.74

Abit

-0.73

цездатний

-0.72

intios

-0.72

POSITIVE LOGITS

<bos>

1.56

 métallique

0.90

 africaine

0.90

 titolata

0.89

 enfans

0.86

 élas

0.83

 africain

0.83

 morire

0.83

 laiton

0.82

 lumineuse

0.81

Activations Density 1.752%

the word "injury" and related terms like "non-"

injury

No Comments

No Known Activations

the word "injury" and related terms like "non-"

injury

No Comments

No Known Activations