INDEX

Explanations

references to sequential actions or steps in a process

oai_token-act-pair · gpt-4o-mini Triggered by @bot

sequence markers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UserScript

-0.68

 propOrder

-0.61

 disambiguazione

-0.57

 speech

-0.52

msgSender

-0.50

awtextra

-0.49

 msglen

-0.48

webElementXpaths

-0.48

AddTagHelper

-0.47

 ujednoznacz

-0.47

POSITIVE LOGITS

 anschließend

0.43

然后

0.41

 THEN

0.40

 потом

0.39

bleib

0.38

然后再

0.38

 ثم

0.37

 kemudian

0.37

 dabei

0.36

 vervolgens

0.36

Activations Density 0.040%

references to sequential actions or steps in a process

sequence markers

No Comments

No Known Activations