INDEX

Explanations

interrogative words and phrases like "why", "how", and "to what extent".

oai_token-act-pair · gemini-2.0-flash

question words

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

we

-0.57

you

-0.49

 they

-0.47

later

-0.46

丁目

-0.44

 người

-0.44

 those

-0.44

 everyone

-0.43

dest

-0.42

 nadie

-0.42

POSITIVE LOGITS

VersionUID

1.00

 initComponents

0.89

IBarButtonItem

0.88

 MainAxisSize

0.86

AnchorStyles

0.82

InvalidProtocol

0.80

 CreateTagHelper

0.77

 autorytatywna

0.76

IntoConstraints

0.76

ConstraintMaker

0.76

Activations Density 0.654%

interrogative words and phrases like "why", "how", and "to what extent".

question words

No Known Activations