INDEX

Explanations

references to the name "Rose" in various contexts

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

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

 houſe

-0.62

 صوتيه

-0.62

 quæ

-0.61

 ſmall

-0.60

achusetts

-0.59

 betweenstory

-0.58

 Houſe

-0.58

tzmann

-0.58

 Monfieur

-0.57

Kaieteur

-0.56

POSITIVE LOGITS

 petals

1.01

Roses

0.77

 petal

0.75

Ros

0.72

 Roses

0.71

Ros

0.70

ROS

0.67

 Rose

0.66

 }}"></

0.65

 يتيمه

0.64

Activations Density 0.121%

references to the name "Rose" in various contexts

No Comments

No Known Activations