INDEX

Explanations

sentences containing words that indicate feelings or thoughts

oai_token-act-pair · gemini-2.0-flash

personal pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 незавершена

-1.13

 Roskov

-1.04

ніципалі

-1.00

abestanden

-0.99

tvguidetime

-0.98

__':

-0.98

 propOrder

-0.96

 doInBackground

-0.96

 Administrativna

-0.96

 disambiguazione

-0.95

POSITIVE LOGITS

me

0.81

him

0.62

us

0.56

 person

0.54

me

0.51

my

0.50

 меня

0.46

oni

0.46

 them

0.44

man

0.44

Activations Density 0.673%

sentences containing words that indicate feelings or thoughts

personal pronouns

No Comments

No Known Activations