INDEX

Explanations

strings and associated variables, possibly identifying code context

oai_token-act-pair · gemini-2.0-flash

strings and variable declarations

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

string

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

 popoli

-0.66

 varandra

-0.66

mybatisplus

-0.66

 soldati

-0.64

 volontà

-0.64

 schuldig

-0.64

 giudi

-0.64

 pronti

-0.63

 colpa

-0.63

 giapp

-0.62

POSITIVE LOGITS

laway

0.68

ouncil

0.66

FTFY

0.59

laar

0.59

id

0.58

loài

0.57

st

0.57

 createState

0.57

ITUTE

0.56

Приятного

0.56

Activations Density 1.363%

strings and associated variables, possibly identifying code context

strings and variable declarations

string

No Comments

No Known Activations