INDEX

Explanations

instances of the word "More" and related phrases indicating additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Biôgrafia

-0.74

ScopeManager

-0.71

 Administrativna

-0.67

tanleria

-0.67

webElementXpaths

-0.58

➌

-0.58



-0.55

IntoConstraints

-0.54

GOTREF

-0.54

viron

-0.54

POSITIVE LOGITS

More

1.17

 More

1.12

 more

1.05

more

1.02

 MORE

0.96

MORE

0.90

 mehr

0.72

 المزيد

0.69

 más

0.68

 więcej

0.68

Activations Density 0.164%

instances of the word "More" and related phrases indicating additional information

No Comments

No Known Activations