INDEX

Explanations

phrases related to actions and behaviors of individuals in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

-0.35

 determine

-0.32

Eventually

-0.31

 Schuster

-0.31

 convirtió

-0.30

Leftrightarrow

-0.30

 Subsequently

-0.29

 acknowledge

-0.29

 combined

-0.29

ことがあります

-0.28

POSITIVE LOGITS



0.81

 autorytatywna

0.78

UrlResolution

0.71

 चीज़ों

0.71

 المعيارى

0.70

Tikang

0.69

 '\\;'

0.69

 betweenstory

0.68

 ſeine

0.67

 queſta

0.66

Activations Density 0.595%

phrases related to actions and behaviors of individuals in various contexts

No Comments

No Known Activations