INDEX

Explanations

questions where someone is being asked to choose something

oai_token-act-pair · gemini-2.0-flash

choices

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Signalez

-1.01

Datuak

-0.98

saraba

-0.98

Personensuche

-0.95

aarrggbb

-0.93

SBATCH

-0.93

évaluateur

-0.92

uxxxx

-0.90

 EconPapers

-0.89

 transfieras

-0.88

POSITIVE LOGITS

↵

0.48

 heavy

0.47

0.45

LETS

0.45

 multi

0.44

or

0.44

 Good

0.44

win

0.44

 Multi

0.43

Mc

0.43

Activations Density 0.664%

questions where someone is being asked to choose something

choices

No Comments

No Known Activations