INDEX

Explanations

the word "sweet" and derivations of it

oai_token-act-pair · gemini-2.0-flash

sweet

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

rungsseite

-0.68

 autorytatywna

-0.64

ніципа

-0.63

AndEndTag

-0.63

 سكانية

-0.54

 Numerade

-0.54

SpringBootTest

-0.53

 changé

-0.52

 EconPapers

-0.49

 nakalista

-0.49

POSITIVE LOGITS

 OFDb

0.61

 calldata

0.57

 MotionEvent

0.55

cerpt

0.55

tonsoft

0.54

 QLabel

0.54

WhereInput

0.52

зулта

0.51

 smelling

0.50

relser

0.50

Activations Density 1.046%

the word "sweet" and derivations of it

sweet

No Comments

No Known Activations