INDEX

Explanations

words related to HP printers and printing functions

oai_token-act-pair · gemini-2.0-flash

technical terms or jargon in computing

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

printers and printing

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

setVerticalGroup

-0.77

#+#

-0.66

 orgasm

-0.60

 <=",

-0.58

enderror

-0.56

parsedMessage

-0.56

 sputnik

-0.55

msgSender

-0.54

 invokingState

-0.53

Discography

-0.52

POSITIVE LOGITS

 pleine

0.54

iders

0.52

GeneratedValue

0.51

bilt

0.50

\{\

0.50

ripsi

0.48

ImageContext

0.48

seite

0.48

ebenarnya

0.47

 punto

0.47

Activations Density 1.681%

words related to HP printers and printing functions

technical terms or jargon in computing

printers and printing

No Comments

No Known Activations