INDEX

Explanations

phrases and concepts related to the significance or irrelevance of various events and opinions

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

Statements of irrelevance or inconsequence

np_acts-logits-general · gemini-2.0-flash

irrelevant or unimportant

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.59

новниш

-0.52

 complètes

-0.51

Filmo

-0.50

boru

-0.50

ेशा

-0.50

 avoient

-0.48

 navideñas

-0.48

 spagno

-0.48

 нельзя

-0.47

POSITIVE LOGITS

 mattered

1.83

 irrelevant

1.78

 matter

1.73

 unimportant

1.67

 matters

1.62

 immaterial

1.52

matters

1.45

matter

1.44

 Matter

1.34

Matter

1.34

Activations Density 0.437%

phrases and concepts related to the significance or irrelevance of various events and opinions

Statements of irrelevance or inconsequence

irrelevant or unimportant

No Comments

No Known Activations