INDEX

Explanations

references to entities, people acting, and owning and fields in general

oai_token-act-pair · gemini-2.0-flash

pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

viewDidLoad

-0.57

makeConstraints

-0.49

NamedQueries

-0.47

igshid

-0.47

לה

-0.47

ciosa

-0.46

__*/

-0.45

 akka

-0.45

oaks

-0.45

mockito

-0.43

POSITIVE LOGITS

 them

3.00

them

2.56

 Them

2.19

Them

2.13

 THEM

2.06

him

1.85

 deles

1.44

 ним

1.29

 őket

1.27

 ellos

1.26

Activations Density 5.046%

references to entities, people acting, and owning and fields in general

pronouns

No Comments

No Known Activations