INDEX

Explanations

specific words that indicate actions, people, or affirmations in a statement

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

Beginning of sentences

np_acts-logits-general · gemini-2.0-flash

various sentence starters or common phrases

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

etheless

-0.87

 nahilalakip

-0.71

لينكات

-0.67

mybatisplus

-0.65

FunctionFlags

-0.65

DoubleQuotes

-0.64

 Administrativna

-0.64

 gawas

-0.63

—

-0.63

URLException

-0.63

POSITIVE LOGITS

documentclass

0.69

<bos>

0.69

 الحره

0.57

 Anſ

0.50

 theſe

0.50

 Wikiseite

0.50

Autoritní

0.49

 firſt

0.46

(/^

0.46

 captioned

0.46

Activations Density 0.602%

specific words that indicate actions, people, or affirmations in a statement

Beginning of sentences

various sentence starters or common phrases

No Comments

No Known Activations