INDEX

Explanations

words related to uncertainty and questioning

oai_token-act-pair · gemini-2.0-flash

wonder

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

 firſt

-0.88

 laſt

-0.87

 fubject

-0.85

 becauſe

-0.84

 myſelf

-0.84

 reaſon

-0.83

 ſeveral

-0.83

 themſelves

-0.83

 beſt

-0.83

 ſtate

-0.82

POSITIVE LOGITS

bootstrapcdn

0.84

帖最后由

0.80

 propOrder

0.80

DockStyle

0.78

انتهای

0.72

ulongan

0.71

WebVitals

0.71

rably

0.71

tagHelperRunner

0.69

ReusableCell

0.68

Activations Density 2.686%

words related to uncertainty and questioning

wonder

No Comments

No Known Activations