INDEX

Explanations

occurrences of the word "and"

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

"And" followed by a section heading

np_acts-logits-general · gemini-2.0-flash

and followed by outlook, discussion, or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 protoimpl

-0.67

 certainly

-0.65

 persino

-0.63

 undoubtedly

-0.62

 zelfs

-0.62

eseorang

-0.61

 addirittura

-0.61

 even

-0.61

 likewise

-0.59

 numberOfRows

-0.58

POSITIVE LOGITS

 Related

0.69

 ITIS

0.64

addCriterion

0.62

ANDO

0.60

aluz

0.60

...:

0.60

 Gibbon

0.59

ussi

0.59

pires

0.58

jic

0.58

Activations Density 0.225%

occurrences of the word "and"

"And" followed by a section heading

and followed by outlook, discussion, or results

No Comments

No Known Activations