INDEX

Explanations

words related to internet communities, including the code parts and version numbers

oai_token-act-pair · gemini-2.0-flash

technical terms and programming keywords

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

Video games

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

gucigalpa

-0.49

 thuyết

-0.47

 επ

-0.47

 MenuView

-0.45

合

-0.45

Cid

-0.44

 pinulongan

-0.43

 Auss

-0.43

astia

-0.41

 Zidane

-0.41

POSITIVE LOGITS

WebControls

0.65

رشف

0.60

TagMode

0.60

VolleyError

0.60

Dac

0.60

 ComVisible

0.60

HasAnnotation

0.59

GIVEREF

0.59

 GeoNames

0.59

modb

0.57

Activations Density 0.797%

words related to internet communities, including the code parts and version numbers

technical terms and programming keywords

Video games

No Comments

No Known Activations