INDEX

Explanations

the word "got"

oai_token-act-pair · gemini-2.0-flash

got

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-1.09

 surla

-1.05

tvguidetime

-1.02

 betweenstory

-1.02

الحياه

-0.96

 nakalista

-0.93

BeginContext

-0.93

bootstrapcdn

-0.86

 typelib

-0.86

aarrggbb

-0.85

POSITIVE LOGITS

("")

0.57

setDo

0.56

al

0.55

Bed

0.54

}?>

0.53

gos

0.50

édez

0.50

ing

0.49

erd

0.48

 straits

0.48

Activations Density 0.927%

the word "got"

got

No Comments

No Known Activations