INDEX

Explanations

references to videos, social media, websites, and real estate.

oai_token-act-pair · gemini-2.0-flash

terms related to video and broadcasting

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

film and tv

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.75

ArgumentParser

-0.64

 propOrder

-0.60

anskje

-0.58

DeleteBehavior

-0.58

complexType

-0.57

 PrintWriter

-0.57

abestanden

-0.57

 Sphinx

-0.57

 BorderRadius

-0.56

POSITIVE LOGITS

 Films

0.68

 broadcast

0.64

TV

0.64

Film

0.64

 Film

0.63

 film

0.63

 broadcasting

0.63

 Broadcast

0.61

tv

0.61

 films

0.61

Activations Density 14.068%

references to videos, social media, websites, and real estate.

terms related to video and broadcasting

film and tv

No Comments

No Known Activations