INDEX

Explanations

occurrences of the word "no" and its variations in different contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 thing

-0.41

 bagay

-0.39

lardan

-0.35

 accordé

-0.35

 things

-0.34

 picado

-0.34

юще

-0.34

it

-0.34

 mati

-0.33

 bastards

-0.33

POSITIVE LOGITS

 στη

0.75

WebElementEntity

0.73

 beim

0.71

 dalla

0.71

 nella

0.69

 dalle

0.69

 autorytatywna

0.68

 sulla

0.68

Vom

0.68

 dallo

0.65

Activations Density 0.126%

occurrences of the word "no" and its variations in different contexts

No Known Activations