INDEX

Explanations

statements about something starting or beginning

oai_token-act-pair · gemini-2.0-flash

start

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

<bos>

-0.57

saturday

-0.49

modb

-0.48

Geografi

-0.47

новништво

-0.47

ibatis

-0.45

ECTOS

-0.45

HasBeenSet

-0.44

ARIUS

-0.44

 defStyleAttr

-0.44

POSITIVE LOGITS

 nakalista

0.63

PyTuple

0.59

QMetaType

0.56

MLLoader

0.56

سكرية

0.55

ValueStyle

0.55

})}

0.53

 scom

0.52

Twin

0.52

appi

0.52

Activations Density 1.732%

statements about something starting or beginning

start

No Comments

No Known Activations