INDEX

Explanations

mentions of "L." followed by other characters

oai_token-act-pair · gemini-2.0-flash

the letter 'L'

np_token-act-pair-logits · gpt-4o-mini

L

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

الحياه

-0.60

 Mares

-0.49

protoc

-0.44

EDEFAULT

-0.44

 intptr

-0.43

 mapStateToProps

-0.43

shub

-0.43

Manbalar

-0.42

}],

-0.41

 ارش

-0.40

POSITIVE LOGITS

rrggbb

0.74

 AssemblyCulture

0.71



0.70

 فريبيس

0.64

 StatelessWidget

0.64

 createSlice

0.64

__()

0.61

########.

0.59

 }}"></

0.59

 Paglinawan

0.58

Activations Density 0.230%

mentions of "L." followed by other characters

the letter 'L'

L

No Comments

No Known Activations