INDEX

Explanations

text related to spending time with friends

oai_token-act-pair · gemini-2.0-flash

Seems to activate contextually for conversational, casual text

np_token-act-pair-logits · gemini-2.0-flash

relaxation, enjoyment

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

TagMode

-0.54

+#+

-0.53

خصة

-0.47

 שוליים

-0.46

<bos>

-0.45

WindowConstants

-0.43

 AssemblyCompany

-0.42

CrossOrigin

-0.41

طفى

-0.40

 String

-0.40

POSITIVE LOGITS

&__

0.59

Clik

0.59

exprimer

0.57

 geleverd

0.57

 Pingback

0.56

jelder

0.55

 gehad

0.55

Eh

0.55

Flo

0.54

шкан

0.54

Activations Density 1.282%

text related to spending time with friends

Seems to activate contextually for conversational, casual text

relaxation, enjoyment

No Comments

No Known Activations